Patent Grant
11011035
The disclosed implementations relates generally to video monitoring, including, but not limited, to monitoring and reviewing motion events in a video stream.
Video surveillance produces a large amount of continuous video data over the course of hours, days, and even months. Such video data includes many long and uneventful portions that are of no significance or interest to a reviewer. In some existing video surveillance systems, motion detection is used to trigger alerts or video recording. However, using motion detection as the only means for selecting video segments for user review may still produce too many video segments that are of no interest to the reviewer. For example, some detected motions are generated by normal activities that routinely occur at the monitored location, and it is tedious and time consuming to manually scan through all of the normal activities recorded on video to identify a small number of activities that warrant special attention. In addition, when the sensitivity of the motion detection is set too high for the location being monitored, trivial movements (e.g., movements of tree leaves, shifting of the sunlight, etc.) can account for a large amount of video being recorded and/or reviewed. On the other hand, when the sensitivity of the motion detection is set too low for the location being monitored, the surveillance system may fail to record and present video data on some important and useful events.
It is a challenge to identify meaningful segments of the video stream and to present them to the reviewer in an efficient, intuitive, and convenient manner. Human-friendly techniques for discovering and presenting motion events of interest both in real-time or at a later time are in great need.
Accordingly, there is a need for video processing with more efficient and intuitive motion event identification, categorization, and presentation. Such methods optionally complement or replace conventional methods for monitoring and reviewing motion events in a video stream.
In some implementations, a method of displaying indicators for motion events on an event timeline is performed at an electronic device (e.g., an electronic device 166,
In some implementations, a method of editing event categories is performed at an electronic device (e.g., the electronic device 166,
In some implementations, a method of categorizing a detected motion event is performed at a computing system (e.g., the client device 504,
In some implementations, a method of generating a smart time-lapse video clip is performed at an electronic device (e.g., the electronic device 166,
In some implementations, a method of performing client-side zooming of a remote video feed is performed at an electronic device (e.g., the electronic device 166,
In accordance with some implementations, a method of processing a video stream is performed at a computing system having one or more processors and memory (e.g., the camera 118,
In accordance with some implementations, a method of categorizing a motion event candidate is performed at a server (e.g., the video server system 508,
In accordance with some implementations, a method of facilitating review of a video recording is performed at a server (e.g., the video server system 508,
In accordance with some implementations, a method of monitoring selected zones in a scene depicted in a video stream is performed at a server (e.g., the video server system 508,
In some implementations, a computing system (e.g., the video server system 508,
Thus, computing systems are provided with more efficient methods for monitoring and facilitating review of motion events in a video stream, thereby increasing the effectiveness, efficiency, and user satisfaction with such systems. Such methods may complement or replace conventional methods for motion event monitoring and presentation.
For a better understanding of the various described implementations, reference should be made to the Description of Implementations below, in conjunction with the following drawings in which like reference numerals refer to corresponding parts throughout the figures.
Like reference numerals refer to corresponding parts throughout the several views of the drawings.
This disclosure provides example user interfaces and data processing systems and methods for video monitoring.
Video-based surveillance and security monitoring of a premises generates a continuous video feed that may last hours, days, and even months. Although motion-based recording triggers can help trim down the amount of video data that is actually recorded, there are a number of drawbacks associated with video recording triggers based on simple motion detection in the live video feed. For example, when motion detection is used as a trigger for recording a video segment, the threshold of motion detection must be set appropriately for the scene of the video; otherwise, the recorded video may include many video segments containing trivial movements (e.g., lighting change, leaves moving in the wind, shifting of shadows due to changes in sunlight exposure, etc.) that are of no significance to a reviewer. On the other hand, if the motion detection threshold is set too high, video data on important movements that are too small to trigger the recording may be irreversibly lost. Furthermore, at a location with many routine movements (e.g., cars passing through in front of a window) or constant movements (e.g., a scene with a running fountain, a river, etc.), recording triggers based on motion detection are rendered ineffective, because motion detection can no longer accurately select out portions of the live video feed that are of special significance. As a result, a human reviewer has to sift through a large amount of recorded video data to identify a small number of motion events after rejecting a large number of routine movements, trivial movements, and movements that are of no interest for a present purpose.
Due to at least the challenges described above, it is desirable to have a method that maintains a continuous recording of a live video feed such that irreversible loss of video data is avoided and, at the same time, augments simple motion detection with false positive suppression and motion event categorization. The false positive suppression techniques help to downgrade motion events associated with trivial movements and constant movements. The motion event categorization techniques help to create category-based filters for selecting only the types of motion events that are of interest for a present purpose. As a result, the reviewing burden on the reviewer may be reduced. In addition, as the present purpose of the reviewer changes in the future, the reviewer can simply choose to review other types of motion events by selecting the appropriate motion categories as event filters.
In addition, in some implementations, event categories can also be used as filters for real-time notifications and alerts. For example, when a new motion event is detected in a live video feed, the new motion event is immediately categorized, and if the event category of the newly detected mention event is a category of interest selected by a reviewer, a real-time notification or alert can be sent to the reviewer regarding the newly detected motion event. In addition, if the new event is detected in the live video feed as the reviewer is viewing a timeline of the video feed, the event indicator and the notification of the new event will have an appearance or display characteristic associated with the event category.
Furthermore, as the types of motion events occurring at different locations and settings can vary greatly, and there are potentially an infinite number of event categories for all motion events collected at the video server system (e.g., the video server system 508). Therefore, it may be undesirable to have a set of fixed event categories from the outset to categorize motion events detected in all video feeds from all camera locations for all users. As disclosed herein, in some implementations, the motion event categories for the video stream from each camera are gradually established through machine learning, and are thus tailored to the particular setting and use of the video camera.
In addition, in some implementations, as new event categories are gradually discovered based on clustering of past motion events, the event indicators for the past events in a newly discovered event category are refreshed to reflect the newly discovered event category. In some implementations, a clustering algorithm with automatic phase out of old, inactive, and/or sparse categories is used to categorize motion events. As a camera changes location, event categories that are no longer active are gradually retired without manual input to keep the motion event categorization model current. In some implementations, user input editing the assignment of past motion events into respective event categories is also taken into account for future event category assignment and new category creation.
Furthermore, for example, within the scene of a video feed, multiple objects may be moving simultaneously. In some implementations, the motion track associated with each moving object corresponds to a respective motion event candidate, such that the movement of the different objects in the same scene may be assigned to different motion event categories.
In general, motion events may occur in different regions of a scene at different times. Out of all the motion events detected within a scene of a video stream over time, a reviewer may only be interested in motion events that occurred within or entered a particular zone of interest in the scene. In addition, the zones of interest may not be known to the reviewer and/or the video server system until long after one or more motion events of interest have occurred within the zones of interest. For example, a parent may not be interested in activities centered around a cookie jar until after some cookies have mysteriously gone missing. Furthermore, the zones of interest in the scene of a video feed can vary for a reviewer over time depending on a present purpose of the reviewer. For example, the parent may be interested in seeing all activities that occurred around the cookie jar one day when some cookies have gone missing, and the parent may be interested in seeing all activities that occurred around a mailbox the next day when some expected mail has gone missing. Accordingly, in some implementations, the techniques disclosed herein allow a reviewer to define and create one or more zones of interest within a static scene of a video feed, and then use the created zones of interest to retroactively identify all past motion events (or all motion events within a particular past time window) that have touched or entered the zones of interest. The identified motion events are optionally presented to the user in a timeline or in a list. In some implementations, real-time alerts for any new motion events that touch or enter the zones of interest are sent to the reviewer. The ability to quickly identify and retrieve past motion events that are associated with a newly created zone of interest addresses the drawbacks of conventional zone monitoring techniques where the zones of interest need to be defined first based on a certain degree of guessing and anticipation that may later prove to be inadequate or wrong, and where only future events (as opposed to both past and future events) within the zones of interest can be identified.
Furthermore, when detecting new motion events that have touched or entered some zone(s) of interest, the event detection is based on the motion information collected from the entire scene, rather than just within the zone(s) of interest. In particular, aspects of motion detection, motion object definition, motion track identification, false positive suppression, and event categorization are all based on image information collected from the entire scene, rather than just within each zone of interest. As a result, context around the zones of interest is taken into account when monitoring events within the zones of interest. Thus, the accuracy of event detection and categorization may be improved as compared to conventional zone monitoring techniques that perform all calculations with image data collected only within the zones of interest.
Other aspects of event monitoring and review for video data are disclosed, including system architecture, data processing pipeline, event categorization, user interfaces for editing and reviewing past events (e.g., event timeline, retroactive coloring of event indicators, event filters based on event categories and zones of interest, and smart time-lapse video summary), notifying new events (e.g., real-time event pop-ups), creating zones of interest, and controlling camera's operation (e.g., changing video feed focus and resolution), and the like. Advantages of these and other aspects will be discussed in more detail later in the present disclosure or will be apparent to persons skilled in the art in light of the disclosure provided herein.
Below,
Reference will now be made in detail to implementations, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the various described implementations. However, it will be apparent to one of ordinary skill in the art that the various described implementations may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the implementations.
It will also be understood that, although the terms first, second, etc. are, in some instances, used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first user interface could be termed a second user interface, and, similarly, a second user interface could be termed a first user interface, without departing from the scope of the various described implementations. The first user interface and the second user interface are both user interfaces, but they are not the same user interface.
The terminology used in the description of the various described implementations herein is for the purpose of describing particular implementations only and is not intended to be limiting. As used in the description of the various described implementations and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises,” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
As used herein, the term “if” is, optionally, construed to mean “when” or “upon” or “in response to determining” or “in response to detecting” or “in accordance with a determination that,” depending on the context. Similarly, the phrase “if it is determined” or “if [a stated condition or event] is detected” is, optionally, construed to mean “upon determining” or “in response to determining” or “upon detecting [the stated condition or event]” or “in response to detecting [the stated condition or event]” or “in accordance with a determination that [a stated condition or event] is detected,” depending on the context.
It is to be appreciated that “smart home environments” may refer to smart environments for homes such as a single-family house, but the scope of the present teachings is not so limited. The present teachings are also applicable, without limitation, to duplexes, townhomes, multi-unit apartment buildings, hotels, retail stores, office buildings, industrial buildings, and more generally any living space or work space.
It is also to be appreciated that while the terms user, customer, installer, homeowner, occupant, guest, tenant, landlord, repair person, and the like may be used to refer to the person or persons acting in the context of some particularly situations described herein, these references do not limit the scope of the present teachings with respect to the person or persons who are performing such actions. Thus, for example, the terms user, customer, purchaser, installer, subscriber, and homeowner may often refer to the same person in the case of a single-family residential dwelling, because the head of the household is often the person who makes the purchasing decision, buys the unit, and installs and configures the unit, and is also one of the users of the unit. However, in other scenarios, such as a landlord-tenant environment, the customer may be the landlord with respect to purchasing the unit, the installer may be a local apartment supervisor, a first user may be the tenant, and a second user may again be the landlord with respect to remote control functionality. Importantly, while the identity of the person performing the action may be germane to a particular advantage provided by one or more of the implementations, such identity should not be construed in the descriptions that follow as necessarily limiting the scope of the present teachings to those particular individuals having those particular identities.
The depicted structure 150 includes a plurality of rooms 152, separated at least partly from each other via walls 154. The walls 154 may include interior walls or exterior walls. Each room may further include a floor 156 and a ceiling 158. Devices may be mounted on, integrated with and/or supported by a wall 154, floor 156 or ceiling 158.
In some implementations, the smart home environment 100 includes a plurality of devices, including intelligent, multi-sensing, network-connected devices, that integrate seamlessly with each other in a smart home network (e.g., 202
In some implementations, the smart home environment 100 includes one or more intelligent, multi-sensing, network-connected wall switches 108 (hereinafter referred to as “smart wall switches 108”), along with one or more intelligent, multi-sensing, network-connected wall plug interfaces 110 (hereinafter referred to as “smart wall plugs 110”). The smart wall switches 108 may detect ambient lighting conditions, detect room-occupancy states, and control a power and/or dim state of one or more lights. In some instances, smart wall switches 108 may also control a power state or speed of a fan, such as a ceiling fan. The smart wall plugs 110 may detect occupancy of a room or enclosure and control supply of power to one or more wall plugs (e.g., such that power is not supplied to the plug if nobody is at home).
In some implementations, the smart home environment 100 of
In some implementations, the smart home environment 100 includes one or more network-connected cameras 118 that are configured to provide video monitoring and security in the smart home environment 100.
The smart home environment 100 may also include communication with devices outside of the physical home but within a proximate geographical range of the home. For example, the smart home environment 100 may include a pool heater monitor 114 that communicates a current pool temperature to other devices within the smart home environment 100 and/or receives commands for controlling the pool temperature. Similarly, the smart home environment 100 may include an irrigation monitor 116 that communicates information regarding irrigation systems within the smart home environment 100 and/or receives control information for controlling such irrigation systems.
By virtue of network connectivity, one or more of the smart home devices of
As discussed above, users may control the smart thermostat and other smart devices in the smart home environment 100 using a network-connected computer or portable electronic device 166. In some examples, some or all of the occupants (e.g., individuals who live in the home) may register their device 166 with the smart home environment 100. Such registration may be made at a central server to authenticate the occupant and/or the device as being associated with the home and to give permission to the occupant to use the device to control the smart devices in the home. An occupant may use their registered device 166 to remotely control the smart devices of the home, such as when the occupant is at work or on vacation. The occupant may also use their registered device to control the smart devices when the occupant is actually located inside the home, such as when the occupant is sitting on a couch inside the home. It should be appreciated that instead of or in addition to registering the devices 166, the smart home environment 100 may make inferences about which individuals live in the home and are therefore occupants and which devices 166 are associated with those individuals. As such, the smart home environment may “learn” who is an occupant and permit the devices 166 associated with those individuals to control the smart devices of the home.
In some implementations, in addition to containing processing and sensing capabilities, the devices 102, 104, 106, 108, 110, 112, 114, 116, and/or 118 (collectively referred to as “the smart devices”) are capable of data communications and information sharing with other smart devices, a central server or cloud-computing system, and/or other devices that are network-connected. The required data communications may be carried out using any of a variety of custom or standard wireless protocols (IEEE 802.15.4, Wi-Fi, ZigBee, 6LoWPAN, Thread, Z-Wave, Bluetooth Smart, ISA100.11a, WirelessHART, MiWi, etc.) and/or any of a variety of custom or standard wired protocols (CAT6 Ethernet, HomePlug, etc.), or any other suitable communication protocol, including communication protocols not yet developed as of the filing date of this document.
In some implementations, the smart devices serve as wireless or wired repeaters. For example, a first one of the smart devices communicates with a second one of the smart devices via a wireless router. The smart devices may further communicate with each other via a connection to one or more networks 162 such as the Internet. Through the one or more networks 162, the smart devices may communicate with a smart home provider server system 164 (also called a central server system and/or a cloud-computing system herein). In some implementations, the smart home provider server system 164 may include multiple server systems each dedicated to data processing associated with a respective subset of the smart devices (e.g., a video server system may be dedicated to data processing associated with camera(s) 118). The smart home provider server system 164 may be associated with a manufacturer, support entity, or service provider associated with the smart device. In some implementations, a user is able to contact customer support using a smart device itself rather than needing to use other communication means, such as a telephone or Internet-connected computer. In some implementations, software updates are automatically sent from the smart home provider server system 164 to smart devices (e.g., when available, when purchased, or at routine intervals).
In some implementations, some low-power nodes are incapable of bidirectional communication. These low-power nodes send messages, but they are unable to “listen”. Thus, other devices in the smart home environment 100, such as the spokesman nodes, cannot send information to these low-power nodes.
As described, the spokesman nodes and some of the low-powered nodes are capable of “listening.” Accordingly, users, other devices, and/or the central server or cloud-computing system 164 may communicate control commands to the low-powered nodes. For example, a user may use the portable electronic device 166 (e.g., a smartphone) to send commands over the Internet to the central server or cloud-computing system 164, which then relays the commands to one or more spokesman nodes in the smart home network 202. The spokesman nodes drop down to a low-power protocol to communicate the commands to the low-power nodes throughout the smart home network 202, as well as to other spokesman nodes that did not receive the commands directly from the central server or cloud-computing system 164.
In some implementations, a smart nightlight 170 is a low-power node. In addition to housing a light source, the smart nightlight 170 houses an occupancy sensor, such as an ultrasonic or passive IR sensor, and an ambient light sensor, such as a photo resistor or a single-pixel sensor that measures light in the room. In some implementations, the smart nightlight 170 is configured to activate the light source when its ambient light sensor detects that the room is dark and when its occupancy sensor detects that someone is in the room. In other implementations, the smart nightlight 170 is simply configured to activate the light source when its ambient light sensor detects that the room is dark. Further, in some implementations, the smart nightlight 170 includes a low-power wireless communication chip (e.g., a ZigBee chip) that regularly sends out messages regarding the occupancy of the room and the amount of light in the room, including instantaneous messages coincident with the occupancy sensor detecting the presence of a person in the room. As mentioned above, these messages may be sent wirelessly, using the mesh network, from node to node (i.e., smart device to smart device) within the smart home network 202 as well as over the one or more networks 162 to the central server or cloud-computing system 164.
Other examples of low-power nodes include battery-operated versions of the smart hazard detectors 104. These smart hazard detectors 104 are often located in an area without access to constant and reliable power and may include any number and type of sensors, such as smoke/fire/heat sensors, carbon monoxide/dioxide sensors, occupancy/motion sensors, ambient light sensors, temperature sensors, humidity sensors, and the like. Furthermore, the smart hazard detectors 104 may send messages that correspond to each of the respective sensors to the other devices and/or the central server or cloud-computing system 164, such as by using the mesh network as described above.
Examples of spokesman nodes include smart doorbells 106, smart thermostats 102, smart wall switches 108, and smart wall plugs 110. These devices 102, 106, 108, and 110 are often located near and connected to a reliable power source, and therefore may include more power-consuming components, such as one or more communication chips capable of bidirectional communication in a variety of protocols.
In some implementations, the smart home environment 100 includes service robots 168 that are configured to carry out, in an autonomous manner, any of a variety of household tasks.
In some implementations, the devices and services platform 300 communicates with and collects data from the smart devices of the smart home environment 100. In addition, in some implementations, the devices and services platform 300 communicates with and collects data from a plurality of smart home environments across the world. For example, the smart home provider server system 164 collects home data 302 from the devices of one or more smart home environments, where the devices may routinely transmit home data or may transmit home data in specific instances (e.g., when a device queries the home data 302). Example collected home data 302 includes, without limitation, power consumption data, occupancy data, HVAC settings and usage data, carbon monoxide levels data, carbon dioxide levels data, volatile organic compounds levels data, sleeping schedule data, cooking schedule data, inside and outside temperature humidity data, television viewership data, inside and outside noise level data, pressure data, video data, etc.
In some implementations, the smart home provider server system 164 provides one or more services 304 to smart homes. Example services 304 include, without limitation, software updates, customer support, sensor data collection/logging, remote access, remote or distributed control, and/or use suggestions (e.g., based on the collected home data 302) to improve performance, reduce utility cost, increase safety, etc. In some implementations, data associated with the services 304 is stored at the smart home provider server system 164, and the smart home provider server system 164 retrieves and transmits the data at appropriate times (e.g., at regular intervals, upon receiving a request from a user, etc.).
In some implementations, the extensible devices and the services platform 300 includes a processing engine 306, which may be concentrated at a single server or distributed among several different computing entities without limitation. In some implementations, the processing engine 306 includes engines configured to receive data from the devices of smart home environments (e.g., via the Internet and/or a network interface), to index the data, to analyze the data and/or to generate statistics based on the analysis or as part of the analysis. In some implementations, the analyzed data is stored as derived home data 308.
Results of the analysis or statistics may thereafter be transmitted back to the device that provided home data used to derive the results, to other devices, to a server providing a webpage to a user of the device, or to other non-smart device entities. In some implementations, use statistics, use statistics relative to use of other devices, use patterns, and/or statistics summarizing sensor readings are generated by the processing engine 306 and transmitted. The results or statistics may be provided via the one or more networks 162. In this manner, the processing engine 306 may be configured and programmed to derive a variety of useful information from the home data 302. A single server may include one or more processing engines.
The derived home data 308 may be used at different granularities for a variety of useful purposes, ranging from explicit programmed control of the devices on a per-home, per-neighborhood, or per-region basis (for example, demand-response programs for electrical utilities), to the generation of inferential abstractions that may assist on a per-home basis (for example, an inference may be drawn that the homeowner has left for vacation and so security detection equipment may be put on heightened sensitivity), to the generation of statistics and associated inferential abstractions that may be used for government or charitable purposes. For example, processing engine 306 may generate statistics about device usage across a population of devices and send the statistics to device users, service providers or other entities (e.g., entities that have requested the statistics and/or entities that have provided monetary compensation for the statistics).
In some implementations, to encourage innovation and research and to increase products and services available to users, the devices and services platform 300 exposes a range of application programming interfaces (APIs) 310 to third parties, such as charities 314, governmental entities 316 (e.g., the Food and Drug Administration or the Environmental Protection Agency), academic institutions 318 (e.g., university researchers), businesses 320 (e.g., providing device warranties or service to related equipment, targeting advertisements based on home data), utility companies 324, and other third parties. The APIs 310 are coupled to and permit third-party systems to communicate with the smart home provider server system 164, including the services 304, the processing engine 306, the home data 302, and the derived home data 308. In some implementations, the APIs 310 allow applications executed by the third parties to initiate specific data processing tasks that are executed by the smart home provider server system 164, as well as to receive dynamic updates to the home data 302 and the derived home data 308.
For example, third parties may develop programs and/or applications, such as web applications or mobile applications, that integrate with the smart home provider server system 164 to provide services and information to users. Such programs and applications may be, for example, designed to help users reduce energy consumption, to preemptively service faulty equipment, to prepare for high service demands, to track past service performance, etc., and/or to perform other beneficial functions or tasks.
In some implementations, the processing engine 306 includes a challenges/rules/compliance/rewards paradigm 410d that informs a user of challenges, competitions, rules, compliance regulations and/or rewards and/or that uses operation data to determine whether a challenge has been met, a rule or regulation has been complied with and/or a reward has been earned. The challenges, rules, and/or regulations may relate to efforts to conserve energy, to live safely (e.g., reducing exposure to toxins or carcinogens), to conserve money and/or equipment life, to improve health, etc. For example, one challenge may involve participants turning down their thermostat by one degree for one week. Those participants that successfully complete the challenge are rewarded, such as with coupons, virtual currency, status, etc. Regarding compliance, an example involves a rental-property owner making a rule that no renters are permitted to access certain owner's rooms. The devices in the room having occupancy sensors may send updates to the owner when the room is accessed.
In some implementations, the processing engine 306 integrates or otherwise uses extrinsic information 412 from extrinsic sources to improve the functioning of one or more processing paradigms. The extrinsic information 412 may be used to interpret data received from a device, to determine a characteristic of the environment near the device (e.g., outside a structure that the device is enclosed in), to determine services or products available to the user, to identify a social network or social-network information, to determine contact information of entities (e.g., public-service entities such as an emergency-response team, the police or a hospital) near the device, to identify statistical or environmental conditions, trends or other information associated with a home or neighborhood, and so forth.
In some implementations, the smart home provider server system 164 or a component thereof serves as the video server system 508. In some implementations, the video server system 508 is a dedicated video processing server that provides video processing services to video sources and client devices 504 independent of other services provided by the video server system 508.
In some implementations, each of the video sources 522 includes one or more video cameras 118 that capture video and send the captured video to the video server system 508 substantially in real-time. In some implementations, each of the video sources 522 optionally includes a controller device (not shown) that serves as an intermediary between the one or more cameras 118 and the video server system 508. The controller device receives the video data from the one or more cameras 118, optionally, performs some preliminary processing on the video data, and sends the video data to the video server system 508 on behalf of the one or more cameras 118 substantially in real-time. In some implementations, each camera has its own on-board processing capabilities to perform some preliminary processing on the captured video data before sending the processed video data (along with metadata obtained through the preliminary processing) to the controller device and/or the video server system 508.
As shown in
In some implementations, the server-side module 506 includes one or more processors 512, a video storage database 514, an account database 516, an I/O interface to one or more client devices 518, and an I/O interface to one or more video sources 520. The I/O interface to one or more clients 518 facilitates the client-facing input and output processing for the server-side module 506. The account database 516 stores a plurality of profiles for reviewer accounts registered with the video processing server, where a respective user profile includes account credentials for a respective reviewer account, and one or more video sources linked to the respective reviewer account. The I/O interface to one or more video sources 520 facilitates communications with one or more video sources 522 (e.g., groups of one or more cameras 118 and associated controller devices). The video storage database 514 stores raw video data received from the video sources 522, as well as various types of metadata, such as motion events, event categories, event category models, event filters, and event masks, for use in data processing for event monitoring and review for each reviewer account.
Examples of a representative client device 504 include, but are not limited to, a handheld computer, a wearable computing device, a personal digital assistant (PDA), a tablet computer, a laptop computer, a desktop computer, a cellular telephone, a smart phone, an enhanced general packet radio service (EGPRS) mobile phone, a media player, a navigation device, a game console, a television, a remote control, a point-of-sale (POS) terminal, vehicle-mounted computer, an ebook reader, or a combination of any two or more of these data processing devices or other data processing devices.
Examples of the one or more networks 162 include local area networks (LAN) and wide area networks (WAN) such as the Internet. The one or more networks 162 are, optionally, implemented using any known network protocol, including various wired or wireless protocols, such as Ethernet, Universal Serial Bus (USB), FIREWIRE, Long Term Evolution (LTE), Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), code division multiple access (CDMA), time division multiple access (TDMA), Bluetooth, Wi-Fi, voice over Internet Protocol (VoIP), Wi-MAX, or any other suitable communication protocol.
In some implementations, the video server system 508 is implemented on one or more standalone data processing apparatuses or a distributed network of computers. In some implementations, the video server system 508 also employs various virtual devices and/or services of third party service providers (e.g., third-party cloud service providers) to provide the underlying computing resources and/or infrastructure resources of the video server system 508. In some implementations, the video server system 508 includes, but is not limited to, a handheld computer, a tablet computer, a laptop computer, a desktop computer, or a combination of any two or more of these data processing devices or other data processing devices.
The server-client environment 500 shown in
Each of the above identified elements may be stored in one or more of the previously mentioned memory devices, and corresponds to a set of instructions for performing a function described above. The above identified modules or programs (i.e., sets of instructions) need not be implemented as separate software programs, procedures, or modules, and thus various subsets of these modules may be combined or otherwise re-arranged in various implementations. In some implementations, the memory 606, optionally, stores a subset of the modules and data structures identified above. Furthermore, the memory 606, optionally, stores additional modules and data structures not described above.
The memory 706 includes high-speed random access memory, such as DRAM, SRAM, DDR RAM, or other random access solid state memory devices; and, optionally, includes non-volatile memory, such as one or more magnetic disk storage devices, one or more optical disk storage devices, one or more flash memory devices, or one or more other non-volatile solid state storage devices. The memory 706, optionally, includes one or more storage devices remotely located from the one or more processing units 702. The memory 706, or alternatively the non-volatile memory within the memory 706, includes a non-transitory computer readable storage medium. In some implementations, the memory 706, or the non-transitory computer readable storage medium of memory 706, stores the following programs, modules, and data structures, or a subset or superset thereof:
Each of the above identified elements may be stored in one or more of the previously mentioned memory devices, and corresponds to a set of instructions for performing a function described above. The above identified modules or programs (i.e., sets of instructions) need not be implemented as separate software programs, procedures, modules or data structures, and thus various subsets of these modules may be combined or otherwise re-arranged in various implementations. In some implementations, memory 706, optionally, stores a subset of the modules and data structures identified above. Furthermore, the memory 706, optionally, stores additional modules and data structures not described above.
In some implementations, at least some of the functions of the video server system 508 are performed by the client device 504, and the corresponding sub-modules of these functions may be located within the client device 504 rather than the video server system 508. In some implementations, at least some of the functions of the client device 504 are performed by the video server system 508, and the corresponding sub-modules of these functions may be located within the video server system 508 rather than the client device 504. The client device 504 and the video server system 508 shown in
The memory 806 includes high-speed random access memory, such as DRAM, SRAM, DDR RAM, or other random access solid state memory devices; and, optionally, includes non-volatile memory, such as one or more magnetic disk storage devices, one or more optical disk storage devices, one or more flash memory devices, or one or more other non-volatile solid state storage devices. The memory 806, or alternatively the non-volatile memory within the memory 806, includes a non-transitory computer readable storage medium. In some implementations, the memory 806, or the non-transitory computer readable storage medium of the memory 806, stores the following programs, modules, and data structures, or a subset or superset thereof:
Each of the above identified elements may be stored in one or more of the previously mentioned memory devices, and corresponds to a set of instructions for performing a function described above. The above identified modules or programs (i.e., sets of instructions) need not be implemented as separate software programs, procedures, or modules, and thus various subsets of these modules may be combined or otherwise re-arranged in various implementations. In some implementations, the memory 806, optionally, stores a subset of the modules and data structures identified above. Furthermore, memory 806, optionally, stores additional modules and data structures not described above.
Attention is now directed towards implementations of user interfaces and associated processes that may be implemented on a respective client device 504 with one or more speakers enabled to output sound, zero or more microphones enabled to receive sound input, and a touch screen 906 enabled to receive one or more contacts and display information (e.g., media content, webpages and/or user interfaces for an application).
Although some of the examples that follow will be given with reference to inputs on touch screen 906 (where the touch sensitive surface and the display are combined), in some implementations, the device detects inputs on a touch-sensitive surface that is separate from the display. In some implementations, the touch sensitive surface has a primary axis that corresponds to a primary axis on the display. In accordance with these implementations, the device detects contacts with the touch-sensitive surface at locations that correspond to respective locations on the display. In this way, user inputs detected by the device on the touch-sensitive surface are used by the device to manipulate the user interface on the display of the device when the touch-sensitive surface is separate from the display. It should be understood that similar methods are, optionally, used for other user interfaces described herein.
Additionally, while the following examples are given primarily with reference to finger inputs (e.g., finger contacts, finger tap gestures, finger swipe gestures, etc.), it should be understood that, in some implementations, one or more of the finger inputs are replaced with input from another input device (e.g., a mouse based input or stylus input). For example, a swipe gesture is, optionally, replaced with a mouse click (e.g., instead of a contact) followed by movement of the cursor along the path of the swipe (e.g., instead of movement of the contact). As another example, a tap gesture is, optionally, replaced with a mouse click while the cursor is located over the location of the tap gesture (e.g., instead of detection of the contact followed by ceasing to detect the contact). Similarly, when multiple user inputs are simultaneously detected, it should be understood that multiple computer mice are, optionally, used simultaneously, or a mouse and finger contacts are, optionally, used simultaneously.
For example, the client device 504 is the portable electronic device 166 (
In
The second region 905 also includes affordances 913 for changing the scale of the event timeline 910: 5 minute affordance 913A for changing the scale of the event timeline 910 to 5 minutes, 1 hour affordance 913B for changing the scale of the event timeline 910 to 1 hour, and affordance 24 hours 913C for changing the scale of the event timeline 910 to 24 hours. In
In
In
In
In
In
In some implementations, the time-lapse video clip is generated by the client device 504, the video server system 508, or a combination thereof. In some implementations, motion events within the selected portion of the event timeline 910 are played at a slower speed than the balance of the selected portion of the event timeline 910. In some implementations, motion events within the selected portion of the event timeline 910 that are assigned to enabled event categories and motion events within the selected portion of the event timeline 910 that touch or overlap enabled zones are played at a slower speed than the balance of the selected portion of the event timeline 910 including motion events assigned to disabled event categories and motion events that touch or overlap disabled zones.
In
In
In
In
In
In some implementations, control and access to the smart home environment 100 is implemented in the operating environment 500 (
The server maintains (1002) the current digital tilt-pan-zoom (DTPZ) settings for the camera. In some implementations, the server stores video settings (e.g., tilt, pan, and zoom settings) for each of the one or more cameras 118 associated with the smart home environment 100.
The camera sends (1004) a video feed at the current DTPZ settings to the server. The server sends (1006) the video feed to the client device. In some implementations, the camera directly sends the video feed to the client device.
The client device presents (1008) the video feed on an associated display.
The client device detects (1010) a first user input.
In response to detecting the first user input, the client device performs (1012) a local software-based zoom on a portion of the video feed according to the first user input.
The client device detects (1014) a second user input. In
In response to detecting the second user input, the client device determines (1016) the current zoom magnification and coordinates of the zoomed-in portion of the video feed. In some implementations, the client device 504 or a component thereof (e.g., camera control module 732,
The client device sends (1018) a zoom command to the server including the current zoom magnification and the coordinates. In some implementations, the client device 504 or a component thereof (e.g., camera control module 732,
In response to receiving the zoom command, the server changes (1020) the stored DTPZ settings for the camera based on the zoom command. In some implementations, the server changes the stored video settings (e.g., tilt, pan, and zoom settings) for the respective camera according to the zoom command. In response to receiving the zoom command, the server sends (1022) the zoom command to the camera including the zoom magnification and the coordinates.
In response to receiving the zoom command, the camera performs (1024) a hardware-based zoom according to the zoom magnification and the coordinates. The respective camera performs a hardware zoom at the zoom magnification on the coordinates indicated by the zoom command. Thus, the respective camera crops its field of view to the coordinates indicated by the zoom command.
After performing the hardware-based zoom, the camera sends (1026) the changed video feed to the server. The respective camera sends the changed video feed with the field of view corresponding to the coordinates indicated by the zoom command. The server sends (1028) the changed video feed to the client device. In some implementations, the camera directly sends the changed video feed to the client device.
The client device presents (1030) the changed video feed on the associated display.
It should be understood that the particular order in which the operations in
In some implementations, after video data is captured at the video source 522, the video data is processed to determine if any potential motion event candidates are present in the video stream. A potential motion event candidate detected in the video data is also referred to as a cue point. Thus, the initial detection of motion event candidates is also referred to as cue point detection. A detected cue point triggers performance of a more through event identification process on a video segment corresponding to the cue point. In some implementations, the more through event identification process includes obtaining the video segment corresponding to the detected cue point, background estimation for the video segment, motion object identification in the video segment, obtaining motion tracks for the identified motion object(s), and motion vector generation based on the obtained motion tracks. The event identification process may be performed by the video source 522 and the video server system 508 cooperatively, and the division of the tasks may vary in different implementations, for different equipment capability configurations, and/or for different network and server load situations. After the motion vector for the motion event candidate is obtained, the video server system 508 categorizes the motion event candidate, and presents the result of the event detection and categorization to a reviewer associated with the video source 522.
In some implementations, the video server system 508 includes functional modules for an event preparer, an event categorizer, and a user facing frontend. The event preparer obtains the motion vectors for motion event candidates (e.g., by processing the video segment corresponding to a cue point or by receiving the motion vector from the video source). The event categorizer categorizes the motion event candidates into different event categories. The user facing frontend generates event alerts and facilitates review of the motion events by a reviewer through a review interface on a client device 504. The client facing frontend also receives user edits on the event categories, user preferences for alerts and event filters, and zone definitions for zones of interest. The event categorizer optionally revises event categorization models and results based on the user edits received by the user facing frontend.
In some implementations, the video server system 508 also determines an event mask for each motion event candidate and caches the event mask for later use in event retrieval based on selected zone(s) of interest.
In some implementations, the video server system 508 stores raw or compressed video data (e.g., in a video data database 1106), event categorization model (e.g., in an event categorization model database 1108), and event masks and other event metadata (e.g., in an event data and event mask database 1110) for each of the video sources 522.
The above is an overview of the system architecture 1102 and the data processing pipeline 1104 for event processing in video monitoring. More details of the processing pipeline and processing techniques are provided below.
As shown in the upper portion of
In some implementations, the video source 522 dynamically determines which parts of the video stream are to be uploaded to the video server system 508 in real-time. For example, in some implementations, depending on the current server load and network conditions, the video source 522 optionally prioritizes the uploading of video segments corresponding newly detected motion event candidates ahead of other portions of the video stream that do not contain any motion event candidates. This upload prioritization helps to ensure that important motion events are detected and alerted to the reviewer in real-time, even when the network conditions and server load are less than optimal. In some implementations, the video source 522 implements two parallel upload connections, one for uploading the continuous video stream captured by the camera 118, and the other for uploading video segments corresponding detected motion event candidates. At any given time, the video source 522 determines whether the uploading of the continuous video stream needs to be suspended temporarily to ensure that sufficient bandwidth is given to the uploading of the video segments corresponding to newly detected motion event candidates.
In some implementations, the video stream uploaded for cloud storage is at a lower quality (e.g., lower resolution, lower frame rate, higher compression, etc.) than the video segments uploaded for motion event processing.
As shown in
As shown in
In some implementations, the beginning of a cue point is the time when the total motion pixel count meets a predetermined threshold (e.g., 50 motion pixels). In some implementations, the start of the motion event candidate corresponding to a cue point is the beginning of the cue point (e.g., t1 in
In some implementations, the thresholds for detecting cue points are adjusted overtime based on performance feedback. For example, if too many false positives are detected, the threshold for motion pixel count is optionally increased. If too many motion events are missed, the threshold for motion pixel count is optionally decreased.
In some implementations, before the profile of the total motion pixel count for a frame sequence is evaluated for cue point detection, the profile is smoothed to remove short dips in total motion pixel count, as shown in
In some implementations, a change in camera state (e.g., IR mode, AE mode, DTPZ settings, etc.) may changes pixel values in the image frames drastically even though no motion has occurred in the scene captured in the video stream. In some implementations, each camera state change is noted in the cue point detection process (as shown in
Sometimes, a fast initial increase in total motion pixel count may indicate a global scene change or a lighting change, e.g., when the curtain is drawn, or when the camera is pointed in a different direction or moved to a different location by a user. In some implementations, as shown in
In some implementations, the cue point detection generally occurs at the video source 522, and immediately after a cue point is detected in the live video stream, the video source 522 sends an event alert to the video server system 508 to trigger the subsequent event processing. In some implementations, the video source 522 includes a video camera with very limited on-board processing power and no controller device, and the cue point detection described herein is performed by the video server system 508 on the continuous video stream transmitted from the camera to the video server system 508.
In some implementations, after a cue point is detected in the video stream, a video segment corresponding to the cue point is used to identify a motion track of a motion object in the video segment. The identification of motion track is optionally performed locally at the video source 522 or remotely at the video server system 508. In some implementations, the identification of the motion track based on a video segment corresponding to a detected cue point is performed at the video server system 508 by an event preparer module. In some implementations, the event preparer module receives an alert for a cue point detected in the video stream, and retrieves the video segment corresponding to the cue point from cloud storage (e.g., the video data database 1106,
In some implementations, after the event preparer module obtains the video segment corresponding to a cue point, the event preparer module performs background estimation, motion object identification, and motion track determination. Once the motion track(s) of the motion obj ect(s) identified in the video segment are determined, the event preparer module generates a motion vector for each of the motion object detected in the video segment. Each motion vector corresponds to one motion event candidate. In some implementations, false positive suppression is optionally performed to reject some motion event candidates before the motion event candidates are submitted for event categorization.
In some implementations, if the video source 522 has sufficient processing capabilities, the background estimation, motion track determination, and the motion vector generation are optionally performed locally at the video source 522.
In some implementations, the motion vector representing a motion event candidate is a simple two-dimensional linear vector defined by a start coordinate and an end coordinate of a motion object in a scene depicted in the video segment, and the motion event categorization is based on the simple two-dimensional linear motion vector. The advantage of using the simple two-dimensional linear motion vector for event categorization is that the event data is very compact, and fast to compute and transmit over a network. When network bandwidth and/or server load is constrained, simplifying the representative motion vector and off-loading the motion vector generation from the event preparer module of the video server system 508 to the video source 522 can help to realize the real-time event categorization and alert generation for many video sources in parallel.
In some implementations, after motion tracks in a video segment corresponding to a cue point are determined, track lengths for the motion tracks are determined. In some implementations, “short tracks” with track lengths smaller than a predetermined threshold (e.g., 8 frames) are suppressed, as they are likely due to trivial movements, such as leaves shifting in the wind, water shimmering in the pond, etc. In some implementations, pairs of short tracks that are roughly opposite in direction are suppressed as “noisy tracks.” In some implementations, after the track suppression, if there are no motion tracks remaining for the video segment, the cue point is determined to be a false positive, and no motion event candidate is sent to the event categorizer for event categorization. If at least one motion track remains after the false positive suppression is performed, a motion vector is generated for each remaining motion track, and corresponds to a respective motion event candidate going into event categorization. In other words, multiple motion event candidates may be generated based on a video segment, where each motion event candidate represents the motion of a respective motion object detected in the video segment. The false positive suppression occurring after the cue point detection and before the motion vector generation is the second layer false positive suppression, which removes false positives based on the characteristics of the motion tracks.
In some implementations, object identification is performed by subtracting the estimated background from each frame of the video segment. A foreground motion mask is then obtained by masking all pixel locations that have no motion pixels. An example of a motion mask is shown in
In some implementations, the motion track is used to generate a two-dimensional linear motion vector which only takes into account the beginning and end locations of the motion track (e.g., as shown by the dotted arrow in
In some implementations, the motion masks corresponding to each motion object detected in the video segment are aggregated across all frames of the video segment to create an event mask for the motion event involving the motion object. As shown in
In some implementations, a motion mask is created based on an aggregation of motion pixels from a short frame sequence in the video segment. The pixel count at each pixel location in the motion mask is the sum of the motion pixel count at that pixel location from all frames in the short frame sequence. All pixel locations in the motion mask with less than a threshold number of motion pixels (e.g., motion pixel count>4 for 10 consecutive frames) are masked. Thus, the unmasked portions of the motion mask for each such short frame sequence indicates a dominant motion region for the short frame sequence. In some implementations, a motion track is optionally created based on the path taken by the dominant motion regions identified from a series of consecutive short frame sequences.
In some implementations, an event mask is optionally generated by aggregating all motion pixels from all frames of the video segment at each pixel location, and masking all pixel locations that have less than a threshold number of motion pixels. The event mask generated this way is no longer a binary event mask, but is a two-dimensional histogram. The height of the histogram at each pixel location is the sum of the number of frames that contain a motion pixel at that pixel location. This type of non-binary event mask is also referred to as a motion energy map, and illustrates the regions of the video scene that are most active during a motion event. The characteristics of the motion energy maps for different types of motion events are optionally used to differentiate them from one another. Thus, in some implementations, the motion energy map of a motion event candidate is vectorized to generate the representative motion vector for use in event categorization. In some implementations, the motion energy map of a motion event is generated and cached by the video server system and used for real-time zone monitoring, and retro-active event identification for newly created zones of interest.
In some implementations, a live event mask is generated based on the motion masks of frames that have been processed, and is continuously updated until all frames of the motion event have been processed. In some implementations, the live event mask of a motion event in progress is used to determine if the motion event is an event of interest for a particular zone of interest. More details of how a live event mask is used for zone monitoring are provided later in the present disclosure.
In some implementations, after the video server system 508 obtains the representative motion vector for a new motion event candidate (e.g., either by generating the motion vector from the video segment corresponding to a newly detected cue point), or by receiving the motion vector from the video source 522, the video server system 508 proceeds to categorize the motion event candidate based on its representative motion vector.
In some implementations, the categorization of motion events (also referred to as “activity recognition”) is performed by training a categorization model based on a training data set containing motion vectors corresponding to various known event categories (e.g., person running, person jumping, person walking, dog running, car passing by, door opening, door closing, etc.). The common characteristics of each known event category that distinguish the motion events of the event category from motion events of other event categories are extracted through the training. Thus, when a new motion vector corresponding to an unknown event category is received, the event categorizer module examines the new motion vector in light of the common characteristics of each known event category (e.g., based on a Euclidean distance between the new motion vector and a canonical vector representing each known event type), and determines the most likely event category for the new motion vector among the known event categories.
Although motion event categorization based on pre-established motion event categories is an acceptable way to categorize motion events, this categorization technique may only be suitable for use when the variety of motion events handled by the video server system 508 is relatively few in number and already known before any motion event is processed. In some implementations, the video server system 508 serves a large number of clients with cameras used in many different environmental settings, resulting in motion events of many different types. In addition, each reviewer may be interested in different types of motion events, and may not know what types of events they would be interested in before certain real world events have happened (e.g., some object has gone missing in a monitored location). Thus, it is desirable to have an event categorization technique that can handle any number of event categories based on actual camera use, and automatically adjust (e.g., create and retire) event categories through machine learning based on the actual video data that is received over time.
In some implementations, categorization of motion events is through a density-based clustering technique (e.g., DBscan) that forms clusters based on density distributions of motion events (e.g., motion events as represented by their respective motion vectors) in a vector event space. Regions with sufficiently high densities of motion vectors are promoted as recognized event categories, and all motion vectors within each promoted region are deemed to belong to a respective recognized event category associated with that promoted region. In contrast, regions that are not sufficiently dense are not promoted or recognized as event categories. Instead, such non-promoted regions are collectively associated with a category for unrecognized events, and all motion vectors within such non-promoted regions are deemed to be unrecognized motion events at the present time.
In some implementations, each time a new motion vector comes in to be categorized, the event categorizer places the new motion vector into the vector event space according to its value. If the new motion vector is sufficiently close to or falls within an existing dense cluster, the event category associated with the dense cluster is assigned to the new motion vector. If the new motion vector is not sufficiently close to any existing cluster, the new motion vector forms its own cluster of one member, and is assigned to the category of unrecognized events. If the new motion vector is sufficiently close to or falls within an existing sparse cluster, the cluster is updated with the addition of the new motion vector. If the updated cluster is now a dense cluster, the updated cluster is promoted, and all motion vectors (including the new motion vector) in the updated cluster are assigned to a new event category created for the updated cluster. If the updated cluster is still not sufficiently dense, no new category is created, and the new motion vector is assigned to the category of unrecognized events. In some implementations, clusters that have not been updated for at least a threshold expiration period are retired. The retirement of old static clusters helps to remove residual effects of motion events that are no longer valid, for example, due to relocation of the camera that resulted in a scene change.
As a background, sequential DB scan allows growth of a cluster based on density reachability and density connectedness. A point q is directly density-reachable from a point p if it is not farther away than a given distance ε (i.e., is part of its ε-neighborhood) and ifp is surrounded by sufficiently many points M such that one may considerp and q to be part of a cluster. q is called density-reachable from p if there is a sequence p1, . . . . pn of points with p1=p and pn=p where each pi+1 is directly density-reachable from pi. Since the relation of density-reachable is not symmetric, another notion of density-connectedness is introduced. Two points p and q are density-connected if there is a point o such that both p and q are density-reachable from o. Density-connectedness is symmetric. A cluster is defined by two properties: (1) all points within the cluster are mutually density-connected, and (2) if a point is density-reachable from any point of the cluster, it is part of the cluster as well. The clusters formed based on density connectedness and density reachability can have all shapes and sizes, in other words, motion event candidates from a video source (e.g., as represented by motion vectors in a dataset) can fall into non-linearly separable clusters based on this density-based clustering algorithm, when they cannot be adequately clustered by K-means or Gaussian Mixture EM clustering techniques. In some implementations, the values of ε and M are adjusted by the video server system 508 for each video source or video stream, such that clustering quality can be improved for different camera usage settings.
In some implementations, during the categorization process, four parameters are stored and sequentially updated for each cluster. The four parameters include: (1) cluster creation time, (2) cluster weight, (3) cluster center, and (4) cluster radius. The creation time for a given cluster records the time when the given cluster was created. The cluster weight for a given cluster records a member count for the cluster. In some implementations, a decay rate is associated with the member count parameter, such that the cluster weight decays over time if an insufficient number of new members are added to the cluster during that time. This decaying cluster weight parameter helps to automatically fade out old static clusters that are no longer valid. The cluster center of a given cluster is the weighted average of points in the given cluster. The cluster radius of a given cluster is the weighted spread of points in the given cluster (analogous to a weighted variance of the cluster). It is defined that clusters have a maximum radius of ε/2. A cluster is considered to be a dense cluster when it contains at least M/2 points. When a new motion vector comes into the event space, if the new motion vector is density-reachable from any existing member of a given cluster, the new motion vector is included in the existing cluster; and if the new motion vector is not density-reachable from any existing member of any existing cluster in the event space, the new motion vector forms its own cluster. Thus, at least one cluster is updated or created when a new motion vector comes into the event space.
After some time, a new motion vector is received and placed in the event space 1114 at time t2. As shown in
Based on the above process, as motion vectors are collected in the event space overtime, the most common event categories emerge gradually without manual intervention. In some implementations, the creation of a new category causes real-time changes in the review interface provided to a client device 504 associated with the video source. For example, in some implementations, as shown in
In some implementations, a user may review past motion events and their categories on the event timeline. In some implementations, the user is allowed to edit the event category assignments, for example, by removing one or more past motion events from a known event category, as shown in
In some implementations, one event category model is established for one camera. In some implementations, a composite model based on the motion events from multiple related cameras (e.g., cameras reported to serve a similar purpose, or have a similar scene, etc.) is created and used to categorize motion events detected in the video stream of each of the multiple related cameras. In such implementations, the timeline for one camera may show event categories discovered based on motion events in the video streams of its related cameras, even though no event for such categories have been seen in the camera's own video stream.
In some implementations, event data and event masks of past motion events are stored in the event data and event mask database 1110 (
In some implementations, the client device 504 passes the user selected filter(s) to the user facing frontend, and the user facing frontend retrieves the events of interest based on the information in the event data and event mask database 1110. In some implementations, the selectable filters include one or more recognized event categories, and optionally any of the categories for unrecognized motion events, rare events, and/or obsolete events. When a recognized event category is selected as a filter, the user facing frontend retrieves all past motion events associated with the selected event category, and present them to the user (e.g., on the timeline, or in an ordered list shown in a review interface). For example, as shown in
In some implementations, in addition to event categories, other types of event filters can also be selected individually or combined with selected event categories. For example, in some implementations, the selectable filters also include a human filter, which can be one or more characteristics associated with events involving a human being. For example, the one or more characteristics that can be used as a human filter include a characteristic shape (e.g., aspect ratio, size, shape, and the like) of the motion object, audio comprising human speech, motion objects having human facial characteristics, etc. In some implementations, the selectable filters also include a filter based on similarity. For example, the user can select one or more example motion events, and be presented one or more other past motion events that are similar to the selected example motion events. In some implementations, the aspect of similarity is optionally specified by the user. For example, the user may select “color content,” “number of moving objects in the scene,” “shape and/or size of motion object,” and/or “length of motion track,” etc, as the aspect(s) by which similarity between two motion events are measured. In some implementations, the user may choose to combine two or more filters and be shown the motion events that satisfy all of the filters combined. In some implementations, the user may choose multiple filters that will act separately, and be shown the motion events that satisfy at least one of the selected filters.
In some implementations, the user may be interested in past motion events that have occurred within a zone of interest. The zone of interest can also be used as an event filter to retrieve past events and generate notifications for new events. In some implementations, the user may define one or more zones of interest in a scene depicted in the video stream. For example, in the user interface shown in
In some implementations, the video server system 508 (e.g., the user facing frontend of the video server system 508) receives the definitions of zones of interest from the client device 504, and stores the zones of interest in association with the reviewer account currently active on the client device 504. When a zone of interest is selected as a filter for reviewing motion events, the user facing frontend searches the event data database 1110 (
In some implementations, the retrospective zone search based on newly created or selected zones of interest is implemented through a regular database query where the relevant features of each past event (e.g., which regions the motion object had entered during the motion event) are determined on the fly, and compared to the zones of interest. In some implementations, the server optionally defines a few default zones of interest (e.g., eight (2×4) predefined rectangular sectors within the scene), and each past event is optionally tagged with the particular default zones of interest that the motion object has entered. In such implementations, the user can merely select one or more of the default zones of interest to retrieve the past events that touched or entered the selected default zones of interest.
In some implementations, event masks (e.g., the example event mask shown in
In some implementations, the scene of the video stream is divided into a grid, and the event mask of each motion event is recorded as an array of flags that indicates whether motion had occurred within each grid location during the motion event. When the zone of interest includes at least one of the grid location at which motion has occurred during the motion event, the motion event is deemed to be relevant to the zone of interest and is retrieved for presentation. In some implementations, the user facing frontend imposes a minimum threshold on the number of grid locations that have seen motion during the motion event, in order to retrieve motion events that have at least the minimum number of grid locations that included motion. In other words, if the motion region of a motion event barely touched the zone of interest, it may not be retrieved for failing to meet the minimum threshold on grid locations that have seen motion during the motion event.
In some implementations, an overlap factor is determined for the event mask of each past motion event and a selected zone of interest, and if the overlapping factor exceeds a predetermined overlap threshold, the motion event is deemed to be a relevant motion event for the selected zone of interest.
In some implementations, the overlap factor is a simple sum of all overlapping grid locations or pixel locations. In some implementations, more weight is given to the central region of the zone of interest than the peripheral region of the zone of interest during calculation of the overlap factor. In some implementations, the event mask is a motion energy mask that stores the histogram of pixel count at each pixel location within the event mask. In some implementations, the overlap factor is weighted by the pixel count at the pixel locations that the motion energy map overlaps with the zone of interest.
By storing the event mask at the time that the motion event is processed, the retrospective search for motion events that are relevant to a newly created zone of interest can be performed relatively quickly, and makes the user experience for reviewing the events-of-interest more seamless. As shown in
In some implementations, the filters can be used for not only past motion events, but also new motion events that have just occurred or are still in progress. For example, when the video data of a detected motion event candidate is processed, a live motion mask is created and updated based on each frame of the motion event as the frame is received by the video server system 508. In other words, after the live event mask is generated, it is updated as each new frame of the motion event is processed. In some implementations, the live event mask is compared to the zone of interest on the fly, and as soon as a sufficient overlap factor is accumulated, an alert is generated, and the motion event is identified as an event of interest for the zone of interest. In some implementations, an alert is presented on the review interface (e.g., as a pop-up) as the motion event is detected and categorized, and the real-time alert optionally is formatted to indicate its associated zone of interest (e.g., similar to the dialog box 928 in
In some implementations, the event mask of the motion event is generated after the motion event is completed, and the determination of the overlap factor is based on a comparison of the completed event mask and the zone of interest. Since the generation of the event mask is substantially in real-time, real-time monitoring of the zone of interest may also be realized this way in some implementations.
In some implementations, if multiple zones of interest are selected at any given time for a scene, the event mask of a new and/or old motion event is compared to each of the selected zones of interest. For a new motion event, if the overlap factor for any of the selected zones of interest exceeds the overlap threshold, an alert is generated for the new motion event as an event of interest associated with the zone(s) that are triggered. For a previously stored motion event, if the overlap factor for any of the selected zones of interest exceeds the overlap threshold, the stored motion event is retrieved and presented to the user as an event of interest associated with the zone(s) that are triggered.
In some implementations, if a live event mask is used to monitor zones of interest, a motion object in a motion event may enter different zones at different times during the motion event. In some implementations, a single alert (e.g., a pop-up notification over the timeline) is generated at the time that the motion event triggers a zone of interest for the first time, and the alert can be optionally updated to indicate the additional zones that are triggered when the live event mask touches those zones at later times during the motion event. In some implementations, one alert is generated for each zone of interest when the live event mask of the motion event touches the zone of interest.
As shown in the upper portion of
Suppose that the motion masks 1118 shown in
In some implementations, a zone of interest is created and selected for zone monitoring. During the zone monitoring, when a new motion event is processed in real-time, an event mask is created in real-time for the new motion event and the event mask is compared to the selected zone of interest. For example, if Zone B is selected for zone monitoring, when the Overlap B is detected, an alert associated with Zone B is generated and sent to the reviewer in real-time.
In some implementations, when a live event mask is used for zone monitoring, the live event mask is updated with the motion mask of each new frame of a new motion event that has just been processed. The live motion mask is compared to the selected zone(s) of interest 1122 at different times (e.g., every 5 frames) during the motion event to determine the overlap factor for each of the zones of interest. For example, if all of zones A, B, and C are selected for zone monitoring, at several times during the new motion event, the live event mask is compared to the selected zones of interest 1122 to determine their corresponding overlap factors. In this example, eventually, two overlap regions are found: Overlap A is an overlap between the event mask 1120 and Zone A, and Overlap B is an overlap between the event mask 1120 and Zone B. No overlap is found between the event mask 1120 and Zone C. Thus, the motion event is identified as an event of interest for both Zone A and Zone B, but not for Zone C. As a result, alerts will be generated for the motion event for both Zone A and Zone B. In some implementations, if the live event mask is compared to the selected zones as the motion mask of each frame is added to the live event mask, Overlap A will be detected before Overlap B, and the alert for Zone A will be triggered before the alert for Zone B.
It is noted that the motion event is detected and categorized independently of the existence of the zones of interest. In addition, the zone monitoring does not rely on raw image information within the selected zones; instead, the zone monitoring can take into account the raw image information from the entire scene. Specifically, the motion information during the entire motion event, rather than the motion information confined within the selected zone, is abstracted into an event mask, before the event mask is used to determine whether the motion event is an event of interest for the selected zone. In other words, the context of the motion within the selected zones is preserved, and the event category of the motion event can be provided to the user to provide more meaning to the zone monitoring results.
In some implementations, control and access to the smart home environment 100 is implemented in the operating environment 500 (
The electronic device displays (1202) a video monitoring user interface on the display including a camera feed from a camera located remotely from the client device in a first region of the video monitoring user interface and an event timeline in a second region of the video monitoring user interface, where the event timeline includes a plurality of event indicators for a plurality of motion events previously detected by the camera. In some implementations, the electronic device (i.e., electronic device 166,
In some implementations, at least one of the height or width of a respective event indicator among the plurality of event indicators on the event timeline corresponds to (1204) the temporal length of a motion event corresponding to the respective event indicator. In some implementations, the event indicators can be no taller or wider than a predefined height/width so as not to clutter the event timeline. In
In some implementations, the video monitoring user interface further includes (1206) a third region with a list of one or more categories, and where the list of one or more categories at least includes an entry corresponding to the first category after associating the first category with the first set of similar motion events. In some implementations, the first, second, and third regions are each located in distinct areas of the video monitoring interface. In some implementations, the list of categories includes recognized activity categories and created zones of interest.
In some implementations, the entry corresponding to the first category includes (1208) a text box for entering a label for the first category. In some implementations, events indicators on the event timeline are colored according to the event category to which they are assigned and also labeled with a text label corresponding to the event category to which they are assigned. For example, in
In some implementations, the entry corresponding to the first category includes (1210) a first affordance for disabling and enabling display of the first set of pre-existing event indicators on the event timeline. In some implementations, the user of the client device is able to filter the event timeline on a category basis (e.g., event categories and/or zones of interest) by disabling view of events indicators associated with unwanted categories.
In some implementations, the entry corresponding to the first category includes (1212) a second affordance for disabling and enabling notifications corresponding to subsequent motion events of the first category. In some implementations, the user of the client device is able to disable reception of notifications for motion events that fall into certain categories.
In some implementations, the second region includes (1214) one or more timeline length affordances for adjusting a resolution of the event timeline. In
In some implementations, an adjustment to the resolution of the timeline causes the event timeline to automatically be repopulated with events indicators based on the selected granularity.
The electronic device associates (1216) a newly created first category with a set of similar motion events (e.g., previously uncategorized events) from among the plurality of motion events previously detected by the camera. In some implementations, the newly created category is a recognized event category or a newly created zone of interest. In some implementations, the client device 504 (
In some implementations, the video server system 508 provides an indication of the set of similar motion events assigned to the newly created first category, and, in response, the client device 504 associates the set of similar motion events with the newly created first category (i.e., by performing operation 1222 or associating the set of similar motion events with the created first category in a local database). In some implementations, the video server system 508 provides event characteristics for the set of similar motion events assigned to the newly created first category, and, in response, the client device 504 associates the set of similar motion events with the newly created first category (i.e., by performing operation 1222 or associating the set of similar motion events with the created first category in a local database).
In some implementations, the newly created category corresponds to (1218) a newly recognized event category. In
In some implementations, the newly created category corresponds to (1220) a newly created zone of interest.
In response to associating the first category with the first set of similar motion events, the electronic device changes (1222) at least one display characteristic for a first set of pre-existing event indicators from among the plurality of event indicators on the event timeline that correspond to the first category, where the first set of pre-existing event indicators correspond to the set of similar motion events. For example, pre-existing uncategorized events indicators on the event timeline that correspond to events that fall into the first event category are retroactively colored a specific color or displayed in a specific shading pattern that corresponds to the first event category. In some implementations, the display characteristic is a fill color of the event indicator, a shading pattern of the event indicator, an icon/symbol overlaid on the event indicator, or the like. In
In some implementations, the set of similar motion events is (1224) a first set of similar motion events, and the electronic device: associates a newly created second category with a second set of similar motion events from among the plurality of motion events previously detected by the camera, where the second set of similar motion events is distinct from the first set of similar motion events; and, in response to associating the second category with the second set of similar motion events, changes at least one display characteristic for a second set of pre-existing event indicators from among the plurality of event indicators on the event timeline that correspond to the second category, where the second set of pre-existing event indicators correspond to the second set of similar motion events. The second set of similar motion events and the second set of pre-existing event indicators are distinct from the first set of similar motion events and the first set of pre-existing event indicators. In
In some implementations, the electronic device detects (1226) a first user input at a location corresponding to a respective event indicator on the event timeline and, in response to detecting the first user input, displays preview of a motion event corresponding to the respective event indicator. For example, the user of the client device 504 hovers over the respective events indicator with a mouse cursor or taps the respective events indicator with his/her finger to display a pop-up preview pane with a short video clip (e.g., approximately three seconds) of the motion event that corresponds to the respective events indicator.
In some implementations, if the event timeline is set to a temporal length of 24 hours and multiple motion events occurred within a short time period (e.g., 60, 300, 600, etc. seconds), the respective events indicator may be associated with the multiple motion events and the pop-up preview pane may concurrently display video clips of the multiple motion event that corresponds to the respective events indicator.
It should be understood that the particular order in which the operations in
In some implementations, control and access to the smart home environment 100 is implemented in the operating environment 500 (
The electronic device displays (1302) a video monitoring user interface on the display with a plurality of affordances associated one or more recognized activities. In some implementations, the electronic device (i.e., electronic device 166,
In some implementations, the video monitoring user interface includes (1304): (A) a first region with a video feed from a camera located remotely from the client device; (B) a second region with an event timeline, where the event timeline includes a plurality event indicators corresponding to motion events, and where at least a subset of the plurality of event indicators are associated with the respective event category; and (C) a third region with a list of one or more recognized event categories.
In some implementations, the list of one or more recognized event categories includes (1306) the plurality of affordances, where each of the plurality of affordances correspond to a respective one of the one or more recognized event categories. In
In some implementations, the respective affordance is displayed (1308) in response to performing a gesture with respect to one of the event indicators. For example, the user hovers over one of the event indicators on the event timeline to display a pop-up box including a video clip of the motion event corresponding to the event indicators and an affordance for accessing the editing user interface corresponding to the respective event category.
The electronic device detects (1310) a user input selecting a respective affordance from the plurality of affordances in the video monitoring user interface, the respective affordance being associated with a respective event category of the one or more recognized event categories.
In response to detecting the user input, the electronic device displays (1312) an editing user interface for the respective event category on the display with a plurality of animated representations in a first region of the editing user interface, where the plurality of animated representations correspond to a plurality of previously captured motion events assigned to the respective event category. In some implementations, an animated representation (i.e., sprites) includes approximately ten frames from a corresponding motion event. For example, the ten frames are the best frames illustrating the captured motion event.
In some implementations, the editing user interface further includes (1314) a second region with a representation of a video feed from a camera located remotely from the client device. In
In some implementations, the representation in the second region includes (1316) a linear motion vector overlaid on the video feed, where the linear motion vector corresponds to a typical motion path for the plurality of previously captured motion events assigned to the respective event category. In
In some implementations, the first region of the editing user interface further includes (1318) an affordance for disabling and enabling notifications corresponding to subsequent motion events of the respective event category. In
In some implementations, the first region of the editing user interface further includes (1320) a text box for entering a label for the respective event category. In
In some implementations, the electronic device detects (1322) one or more subsequent user inputs selecting one or more animated representations in the first region of the editing user interface and, in response to detecting the one or more subsequent user inputs, sends a message to a server indicating the one or more selected animated representations, where a set of previously captured motion events corresponding to the one or more selected animated representations are disassociated with the respective event category. In some implementations, the user of the client device 504 removes animated representations for motion events that are erroneously assigned to the event category. In some implementations, the client device 504 sends a message to the video server system 508 indicating the removed motion events, and, subsequently, the video server system 508 or a component thereof (e.g., event categorization module 622,
In
It should be understood that the particular order in which the operations in
In some implementations, control and access to the smart home environment 100 is implemented in the operating environment 500 (
The computing system displays (1402) a video monitoring user interface on the display including a video feed from a camera located remotely from the client device in a first region of the video monitoring user interface and an event timeline in a second region of the video monitoring user interface, where the event timeline includes one or more event indicators corresponding to one or more motion events previously detected by the camera. In some implementations, the client device 504 or a component thereof (e.g., event review interface module 734,
The computing system detects (1404) a motion event. In some implementations, the client device 504 (
The computing system determines (1406) one or more characteristics for the motion event. For example, the one or more characteristics include the motion direction, linear motion vector for the motion event, the time of the motion event, the area in the field-of-view of the respective in which the motion event is detected, a face or item recognized in the captured motion event, and/or the like.
In accordance with a determination that the one or more determined characteristics for the motion event satisfy one or more criteria for a respective category, the computing system (1408): assigns the motion event to the respective category; and displays an indicator for the detected motion event on the event timeline with a display characteristic corresponding to the respective category. In some implementations, the one or more criteria for the respective event category include a set of event characteristics (e.g., motion vector, event time, model/cluster similarity, etc.), whereby the motion event is assigned to the event category if its determined characteristics match a certain number of event characteristics for the category. In some implementations, the client device 504 (
In some implementations, the respective category corresponds to (1410) a recognized event category. In some implementations, the client device 504, the video server system 508 (
In some implementations, the respective category corresponds to (1412) a previously created zone of interest. In some implementations, the client device 504, the video server system 508 (
In some implementations, in accordance with a determination that the one or more determined characteristics for the motion event satisfy the one or more criteria for the respective category, the computing system or a component thereof (e.g., the notification module 738,
In some implementations, the notification pops-up (1416) from the indicator for the detected motion event. In
In some implementations, the notification is overlaid (1418) on the video in the first region of the video monitoring user interface. In some implementations, for example, the notification 928 in
In some implementations, the notification is (1420) a banner notification displayed in a location corresponding to the top of the video monitoring user interface. In some implementations, for example, the notification 928 in
In some implementations, the notification includes (1422) one or more affordances for providing feedback as to whether the detected motion event is properly assigned to the respective category. In some implementations, for example, the notification 928 in
It should be understood that the particular order in which the operations in
In some implementations, control and access to the smart home environment 100 is implemented in the operating environment 500 (
The electronic device displays (1502) a video monitoring user interface on the display including a video feed from a camera located remotely from the client device in a first region of the video monitoring user interface and an event timeline in a second region of the video monitoring user interface, where the event timeline includes a plurality of event indicators for a plurality of motion events previously detected by the camera. In some implementations, the electronic device (i.e., electronic device 166,
The electronic device detects (1504) a first user input selecting a portion of the event timeline, where the selected portion of the event timeline includes a subset of the plurality of event indicators on the event timeline. For example, the user of the client device selects the portion of the event timeline by inputting a start and end time or using a sliding, adjustable window overlaid on the timeline. In
In response to the first user input, the electronic device causes (1506) generation of a time-lapse video clip of the selected portion of the event timeline. In some implementations, after selecting the portion of the event timeline, the client device 504 causes generation of the time-lapse video clip corresponding to the selected portion by the client device 504, the video server system 508 or a component thereof (e.g., event post-processing module 634,
In some implementations, prior to detecting the first user input selecting the portion of the event timeline, the electronic device (1508): detects a third user input selecting a time-lapse affordance within the video monitoring user interface; and, in response to detecting the third user input, displays at least one of (A) an adjustable window overlaid on the event timeline for selecting the portion of the event timeline and (B) one or more text entry boxes for entering times for a beginning and an end of the portion of the event timeline. In some implementations, the first user input corresponds to the adjustable window or the one or more text entry boxes. In
In some implementations, causing generation of the time-lapse video clip further comprises (1510) sending an indication of the selected portion of the event timeline to a server so as to generate the time-lapse video clip of the selected portion of the event timeline. In some implementations, after detecting the first user input selecting the portion of the event timeline, the client device 504 causes the time-lapse video clip to be generated by sending an indication of the start time (e.g., 12:20:00 pm according to the start time entry box 956A in
In some implementations, causing generation of the time-lapse video clip further comprises (1512) generating the time-lapse video clip from stored video footage based on the selected portion of the event timeline and timing of the motion events corresponding to the subset of the plurality of event indicators within the selected portion of the event timeline. In some implementations, after detecting the first user input selecting the portion of the event timeline, the client device 504 generates the time-lapse video clip from stored footage according to the start time (e.g., 12:20:00 pm according to the start time entry box 956A in
In some implementations, causing generation of the time-lapse video clip further comprises (1514) detecting a third user input selecting a temporal length for the time-lapse video clip. In some implementations, prior to generation of the time-lapse video clip and after selecting the portion of the event timeline, the client device 504 displays a dialog box or menu pane that enables the user of the client device 504 to select a length of the time-lapse video clip (e.g., 30, 60, 90, etc. seconds). For example, the user selects a two hour portion of the event timeline for the time-lapse video clip and then selects a 60 second length for the time-lapse video clip which causes the selected 2 hour portion of the event timeline to be compressed to 60 seconds in length.
In some implementations, after causing generation of the time-lapse video clip, the electronic device displays (1516) a first notification within the video monitoring user interface indicating processing of the time-lapse video clip. For example, the first notification is a banner notification indicating the time left in generating/processing of the time-lapse video clip.
The electronic device displays (1518) the time-lapse video clip of the selected portion of the event timeline, where motion events corresponding to the subset of the plurality of event indicators are played at a slower speed than the remainder of the selected portion of the event timeline. For example, during playback of the time-lapse video clip, motion events are displayed at 2× or 4× speed and other portions of the video feed within the selection portion are displayed at 16× or 32× speed.
In some implementations, prior to displaying the time-lapse video clip, the electronic device (1520): displays a second notification within the video monitoring user interface indicating completion of generation for the time-lapse video clip; and detects a fourth user input selecting the second notification. In some implementations, displaying the time-lapse video clip further comprises displaying the time-lapse video clip in response to detecting the fourth input. For example, the second notification is a banner notification indicating that generation of the time-lapse video clip is complete. At a time subsequent to
In some implementations, prior to displaying the time-lapse video clip, the electronic device detects (1522) selection of the time-lapse video clip from a collection of saved video clips. In some implementations, displaying the time-lapse video clip further comprises displaying the time-lapse video clip in response to detecting selection of the time-lapse video clip. In some implementations, the server video server system 508 stores a collection of saved video clips (e.g., in the video storage database 516,
In some implementations, the electronic device detects (1524) one or more second user inputs selecting one or more categories associated with the plurality of motion events. In some implementations, causing generation of the time-lapse video clip further comprises causing generation of the time-lapse video clip of the selected portion of the event timeline based on the one or more selected categories, and displaying the time-lapse video clip further comprises displaying the time-lapse video clip of the selected portion of the event timeline, where motion events corresponding to the subset of the plurality of event indicators assigned to the one or more selected categories are played at a slower speed than the remainder of the selected portion of the event timeline. In some implementations, the one or more selected categories include (1526) at least one of a recognized event category or a previously created zone of interest. In some implementations, the user of the client device 504 is able to enable/disable zones and/or event categories prior to generating the time-lapse video clip. For example, the motion events assigned to enabled event categories and motion events that touch or overlap enabled zones are played at a slower speed during the time-lapse than the balance of the selected portion of the event timeline including motion events assigned to disabled event categories and motion events that touch or overlap disabled zones.
In
It should be understood that the particular order in which the operations in
In some implementations, control and access to the smart home environment 100 is implemented in the operating environment 500 (
The electronic device receives (1602) a first video feed from a camera located remotely from the client device with a first field of view. In some implementations, the electronic device (i.e., electronic device 166,
The electronic device displays (1604), on the display, the first video feed in a video monitoring user interface. In some implementations, the client device 504 or a component thereof (e.g., event review interface module 734,
The electronic device detects (1606) a first user input to zoom in on a respective portion of the first video feed. In some implementations, the first user input is a mouse scroll wheel, keyboard shortcuts, or selection of a zoom-in affordance (e.g., elevator bar or other widget) in a web browser accompanied by a dragging gesture to pane the zoomed region. For example, the user of the client device 504 is able to drag the handle 919 of the elevator bar in
In some implementations, the display is (1608) a touch-screen display, and where the first user input is a pinch-in gesture performed on the first video feed within the video monitoring user interface. In some implementations, the first user input is a pinch-in gesture on a touch screen of the electronic device.
In response to detecting the first user input, the electronic device performs (1610) a software zoom function on the respective portion of the first video feed to display the respective portion of the first video feed in a first resolution. In some implementations, the first user input determines a zoom magnification for the software zoom function. For example, the width between contacts of a pinch gesture determines the zoom magnification. In another example, the length of a dragging gesture on an elevator bar associated with zooming determines the zoom magnification.
In some implementations, in response to detecting the first user input, the electronic device displays (1612) a perspective window within the video monitoring user interface indicating a location of the respective portion relative to the first video feed. In some implementations, after performing the software zoom, a perspective window is displayed in the video monitoring UI which shows the zoomed region's location relative to the first video feed (e.g., picture-in-picture window).
In some implementations, prior to the determining and the sending, the electronic device detects (1614) a second user input within the video monitoring user interface selecting a video enhancement affordance. In some implementations, the determining operation 1618 and the sending operation 1620 are performed in response to detecting the second user input. In
In some implementations, in response to detecting the second user input and prior to performing the sending operation 1620, the electronic device displays (1616) a warning message indicating that saved video footage will be limited to the respective portion. In some implementations, after selecting the enhancement affordance to hardware zoom in on the respective portion, only footage from the respective portion (i.e., the cropped region) will be saved by the video server system 508. Prior to selecting the enhancement affordance, the video server system 508 saved the entire field of view of the respective camera shown in the first video feed, not the software zoomed version.
The electronic device determines (1618) a current zoom magnification of the software zoom function and coordinates of the respective portion of the first video feed. In some implementations, the client device 504 or a component thereof (e.g., camera control module 732,
The electronic device sends (1620) a command to the camera to perform a hardware zoom function on the respective portion according to the current zoom magnification and the coordinates of the respective portion of the first video feed. In some implementations, the client device 504 or a component thereof (e.g., camera control module 732,
The electronic device receives (1622) a second video feed from the camera with a second field of view different from the first field of view, where the second field of view corresponds to the respective portion. For example, the second video feed is a cropped version of the first video feed that only includes the respective portion in its field-of-view, but with higher resolution than the local software zoomed version of the respective portion.
The electronic device displays (1624), on the display, the second video feed in the video monitoring user interface, where the second video feed is displayed in a second resolution that is higher than the first resolution.
In some implementations, the video monitoring user interface includes (1626) an affordance for resetting the camera to display the first video feed after displaying the second video feed. In some implementations, after performing the hardware zoom, the user of the client device 504 is able to reset the zoom configuration to the original video feed. In
It should be understood that the particular order in which the operations in
In this representative method, the start of a motion event candidate is detected in a live video stream, which then triggers the subsequent processing (e.g., motion track and motion vector generation) and categorization of the motion event candidate. A simple spatial motion vector, such as a linear motion vector is optionally used to represent the motion event candidate in the event categorization process to improve processing efficiency (e.g., speed and data compactness).
As shown in
The computing system processes (1702) the video stream to detect a start of a first motion event candidate in the video stream. In response to detecting the start of the first motion event candidate in the video stream, the computing system initiates (1704) event recognition processing on a first video segment associated with the start of the first motion event candidate, where initiating the event recognition processing further includes the following operations: determining a motion track of a first object identified in the first video segment; generating a representative motion vector for the first motion event candidate based on the respective motion track of the first object; and sending the representative motion vector for the first motion event candidate to an event categorizer, where the event categorizer assigns a respective motion event category to the first motion event candidate based on the representative motion vector of the first motion event candidate.
In some implementations, at least one of processing the video stream, determining the motion track, generating the representative motion vector, and sending the representative motion vector to the event categorizer is (1706) performed locally at the source of the video stream. For example, in some implementations, the camera 118 may perform one or more of the initial tasks locally before sending the rest of the tasks to the cloud for the server to complete. In some implementations, all of the above tasks are performed locally at the camera 118 or the video source 522 comprising the camera 118 and a controller device.
In some implementations, at least one of processing the video stream, determining the motion track, generating the representative motion vector, and sending the representative motion vector to the categorization server is (1708) performed at a server (e.g., the video server system 508) remote from the source of the video stream (e.g., video source 522). In some implementations, all of the above tasks are performed at the server, and the video source is only responsible for streaming the video to the server over the one or more networks 162 (e.g., the Internet).
In some implementations, the computing system includes (1710) at least the source of the video stream (e.g., the video source 522) and a remote server (e.g., the video server system 508), and the source of the video stream dynamically determines whether to locally perform the processing of the video stream, the determining of the motion track, and the generating of the representative motion vector, based on one or more predetermined distributed processing criteria. For example, in some implementations, the camera dynamically determines how to divide up the above tasks based on the current network conditions, the local processing power, the number and frequency of motion events that are occurring right now or on average, the current load on the server, the time of day, etc.
In some implementations, in response to detecting the start of the first motion event candidate, the computing system (e.g., the video source 522) uploads (1712) the first video segment from the source of the video stream to a remote server (e.g., the video server system 508), where the first video segment begins at a predetermined lead time (e.g., 5 seconds) before the start of the first motion event candidate and lasts a predetermined duration (e.g., 30 seconds). In some implementations, the uploading of the first video segment is in addition to the regular video stream uploaded to the video server system 508.
In some implementations, when uploading the first video segment from the source of the video stream to the remote server: the computing system (e.g., the video source 522), in response to detecting the start of the first motion event candidate, uploads (1714) the first video segment at a higher quality level as compared to a normal quality level at which video data is uploaded for cloud storage. For example, in some implementations, a high resolution video segment is uploaded for motion event candidates detected in the video stream, so that the video segment can be processed in various ways (e.g., zoomed, analyzed, filtered by zones, filtered by object types, etc.) in the future. Similarly, in some implementations, the frame rate of the video segment for detected event candidate is higher that the video data uploaded for cloud storage.
In some implementations, in response to detecting the start of the first motion event candidate, the computing system (e.g., the event preparer of the video server system 508) extracts (1716) the first video segment from cloud storage (e.g., video data database 1106,
In some implementations, to process the video stream to detect the start of the first motion event candidate in the video stream: the computing system performs (1718) the following operations: obtaining a profile of motion pixel counts for a current frame sequence in the video stream; in response to determining that the obtained profile of motion pixel counts meet a predetermined trigger criterion (e.g., total motion pixel count exceeds a predetermined threshold), determining that the current frame sequence includes a motion event candidate; identifying a beginning time for a portion of the profile meeting the predetermined trigger criterion; and designating the identified beginning time to be the start of the first motion event candidate. This is part of the processing pipeline 1104 (
In some implementations, the computing system receives (1720) a respective motion pixel count for each frame of the video stream from a source of the video stream. In some implementations, the respective motion pixel count is adjusted (1722) for one or more of changes of camera states during generation of the video stream. For example, in some implementations, the adjustment based on camera change (e.g., suppressing the motion event candidate altogether if the cue point overlaps with a camera state change) is part of the false positive suppression process performed by the video source. The changes in camera states include camera events such as IR mode change or AE change, and/or camera system reset.
In some implementations, to obtain the profile of motion pixel counts for the current frame sequence in the video stream, the computing system performs (1724) the following operations: generating a raw profile based on the respective motion pixel count for each frame in the current frame sequence; and generating the profile of motion pixel counts by smoothing the raw profile to remove one or more temporary dips in pixel counts in the raw profile. This is illustrated in
In some implementations, to determine the motion track of the object identified in the first video segment, the computing system performs (1726) the following operations: based on a frame sequence of the first video segment: (1) performing background estimation to obtain a background for the first video segment; (2) performing object segmentation to identify one or more foreground objects in the first video segment by subtracting the obtained background from the frame sequence, the one or more foreground object including the object; and (3) establishing a respective motion track for each of the one or more foreground objects by associating respective motion masks of the foreground object across multiple frames of the frame sequence. The motion track generation is described in more detail in
In some implementations, the computing system determines (1728) a duration of the respective motion track for each of the one or more foreground objects, discards (1730) zero or more respective motion tracks and corresponding foreground objects if the durations of the respective zero or more motion tracks are shorter than a predetermined duration (e.g., 8 frames). This is optionally included as part of the false positive suppression process. Suppression of super short tracks helps to prune off movements such as leaves in a tree, etc.
In some implementations, to perform the object segmentation to identify one or more foreground objects and establish the respective motion track for each of the one or more foreground objects, the computing system performs (1732) the following operations: building a histogram of foreground pixels identified in the frame sequence of the first video segment, where the histogram specifies a frame count for each pixel location in a scene of the first video segment; filtering the histogram to remove regions below a predetermined frame count; segmenting the filtered histogram into the one or more motion regions; and selecting one or more dominant motion regions from the one or more motion regions based on a predetermined dominance criterion (e.g., regions containing at least a threshold of frame count/total motion pixel count), where each dominant motion region corresponds to the respective motion track of a corresponding one of the one or more foreground objects.
In some implementations, the computing system generates a respective event mask for the foreground object corresponding to a first dominant motion region of the one or more dominant regions based on the first dominant motion region. The event mask for each object in motion is stored and optionally used to filter the motion event including the object in motion at a later time.
It should be understood that the particular order in which the operations in
In this method 1800, mathematical processing of motion vectors (e.g., linear motion vectors) is performed, including clustering and rejection of false positives. Although the method 1800 occurs on the server, the generation of the motion vector may occur locally at the camera or at the server. The motion vectors are generated in real-time based on live motion events detected in a live video stream captured by a camera.
In some implementations, a clustering algorithm (e.g., DBscan) is used in the process. This clustering algorithm allows the growth of clusters into any shapes. A cluster is promoted as a dense cluster based on its cluster weight, which is in turn based at least partially on the number of motion vectors contained in it. Only dense clusters are recognized as categories of recognized events. A user or the server can give a category name to each category of recognized events. A cluster is updated when a new vector falls within the range of the cluster. If a cluster has not been updated for a long time, the cluster and its associated event category is optionally deleted (e.g., via a decay factor applied to the cluster weight). In some implementations, if a cluster remains sparse for a long time, the cluster is optionally deleted as noise.
As shown in
In response to receiving the respective motion vector for each of the series of motion event candidates, the server determines (1804) a spatial relationship between the respective motion vector of said each motion event candidate to one or more existing clusters established based on a plurality of previously processed motion vectors. This is illustrated in
In accordance with a determination that the respective motion vector of a first motion event candidate of the series of motion event candidates falls within a respective range of at least a first existing cluster of the one or more existing clusters, the server assigns (1806) the first motion event candidate to at least a first event category associated with the first existing cluster.
In some implementations, the first event category is (1808) a category for unrecognized events. This occurs when the first event category has not yet been promoted as a dense cluster and given its own category.
In some implementations, the first event category is (1810) a category for recognized events. This occurs when the first event category has already been promoted as a dense cluster and given its own category.
In some implementations, in accordance with a determination that the respective motion vector of a second motion event candidate of the series of motion event candidates falls beyond a respective range of any existing cluster, the server performs (1812) the following operations: assigning the second motion event candidate to a category for unrecognized events; establishing a new cluster for the second motion event candidate; and associating the new cluster with the category for unrecognized events. This describes a scenario where a new motion vector does not fall within any existing cluster in the event space, and the new motion vector forms its own cluster in the event space. The corresponding motion event of the new motion vector is assigned to the category for unrecognized events.
In some implementations, the server stores (1814) a respective cluster creation time, a respective current cluster weight, a respective current cluster center, and a respective current cluster radius for each of the one or more existing clusters. In accordance with the determination that the respective motion vector of the first motion event candidate of the series of motion event candidates falls within the respective range of the first existing cluster, the server updates (1816) the respective current cluster weight, the respective current cluster center, and the respective current cluster radius for the first existing cluster based on a spatial location of the respective motion vector of the first motion event candidate.
In some implementations, before the updating, the first existing cluster is associated with a category of unrecognized events, and after the updating, the server determines (1818) a respective current cluster density for the first existing cluster based on the respective current cluster weight and the respective current cluster radius of the first existing cluster. In accordance with a determination that the respective current cluster density of the first existing cluster meets a predetermined cluster promotion density threshold, the server promotes (1820) the first existing cluster as a dense cluster. In some implementations, promoting the first existing cluster further includes (1822) the following operations: creating a new event category for the first existing cluster; and disassociating the first existing cluster from the category of unrecognized events.
In some implementations, after disassociating the first existing cluster from the category of unrecognized events, the server reassigns (1824) all motion vectors in the first existing cluster into the new event category created for the first existing cluster. This describes the retroactive updating of event categories for past motion events, when new categories are created.
In some implementations, before the updating, the first existing cluster is (1826) associated with a category of unrecognized events, and in accordance with a determination that the first existing cluster has included fewer than a threshold number of motion vectors for at least a threshold amount of time since the respective cluster creation time of the first existing cluster, the server performs (1828) the following operations: deleting the first existing cluster including all motion vectors currently in the first existing cluster; and removing the motion event candidates corresponding to the deleted motion vectors from the category of unrecognized events. This describes the pruning of sparse clusters, and motion event candidates in the sparse clusters, for example, as shown in
In some implementations, the first existing cluster is (1830) associated with a category of recognized events, and in accordance with a determination that the first existing cluster has not been updated for at least a threshold amount of time, the server deletes (1832) the first existing cluster including all motion vectors currently in the first existing cluster. In some implementations, the server further removes (1834) the motion event candidates corresponding to the deleted motion vectors from the category of recognized events, and deletes (1836) the category of recognized events. This describes the retiring of old inactive clusters. For example, if the camera has been moved to a new location, over time, old event categories associated with the previous location are automatically eliminated without manual intervention.
In some implementations, the respective motion vector for each of the series of motion event candidates includes (1838) a start location and an end location of a respective object in motion detected a respective video segment associated with the motion event candidate. The motion vector of this form is extremely compact, reducing processing and transmission overhead.
In some implementations, to obtain the respective motion vector for each of the series of motion event candidates in real-time as said each motion event candidate is detected in a live video stream, the server receives (1840) the respective motion vector for each of the series of motion event candidates in real-time from a camera capturing the live video stream as said each motion event candidate is detected in the live video stream by the camera. In some implementations, the representative motion vector is a small piece of data received from the camera, where the camera has processed the captured video data in real-time and identified motion event candidate. The camera sends the motion vector and the corresponding video segment to the server for more sophisticated processing, e.g., event categorization, creating the event mask, etc.
In some implementations, to obtain the respective motion vector for each of the series of motion event candidates in real-time as said each motion event candidate is detected in a live video stream, the server performs (1842) the following operations: identifying at least one object in motion in a respective video segment associated with the motion event candidate; determining a respective motion track of the at least one object in motion within a predetermined duration; and generating the respective motion vector for the motion event candidate based on the determined respective motion track of the at least one object in motion.
It should be understood that the particular order in which the operations in
In some implementations, the non-causal (or retrospective) zone search based on newly created zones of interest is based on event masks of the past motion events that have been stored at the server. The event filtering based on selected zones of interest can be applied to past motion events, and to motion events that are currently being detected in the live video stream.
As shown in
The server stores (1904) a respective event mask for each of the plurality of motion events identified in the video recording, the respective event mask including an aggregate of motion pixels associated with the at least one object in motion over multiple frames of the motion event. For example, in some implementations, each event includes one object in motion, and corresponds to one event mask. Each scene may have multiple motion events occurring at the same time, and have multiple objects in motion in it.
The server receives (1906) a definition of a zone of interest within the scene depicted in the video recording. In some implementations, the definition of the zone of interest is provided by a user or is a default zone defined by the server. Receiving the definition of the zone can also happen when a reviewer is reviewing past events, and has selected a particular zone that is already defined as an event filter.
In response to receiving the definition of the zone of interest, the server performs (1908) the following operations: determining, for each of the plurality of motion events, whether the respective event mask of the motion event overlaps with the zone of interest by at least a predetermined overlap factor (e.g., a threshold number of overlapping pixels between the respective event mask and the zone of interest); and identifying one or more events of interest from the plurality of motion events, where the respective event mask of each of the identified events of interest is determined to overlap with the zone of interest by at least the predetermined overlap factor. In some implementations, motion events that touched or entered the zone of interest are identified as events of interest. The events of interest may be given a colored label or other visual characteristics associated with the zone of interest, and presented to the reviewer as a group. It is worth noting that the zone of interest is created after the events have already occurred and been identified. The fact that the event masks are stored at the time that the motion events were detected and categorized provides an easy way to go back in time and identify motion events that intersect with the newly created zone of interest.
In some implementations, the server generates (1910) the respective event mask for each of the plurality of motion events, where the generating includes: creating a respective binary motion pixel map for each frame of the respective video segment associated with the motion event; and combining the respective binary motion pixel maps of all frames of the respective video segment to generate the respective event mask for the motion event. As a result, the event mask is a binary map that is active (e.g., 1) at all pixel locations where the object in motion has reached in at least one frame of the video segment. In some implementations, some other variations of event mask are optionally used, e.g., giving higher weight to pixel locations that the object in motion has reached in multiple frames, such that this information may be taken into account when determining the degree of overlap between the event mask and the zone of interest. More details of the generation of the event mask are provided in
In some implementations, the server receives (1912) a first selection input from the user to select the zone of interest as a first event filter, and visually labels (1914) the identified events of interest with a respective indicator associated with the zone of interest in an event review interface. This is illustrated in
In some implementations, the server receives (1916) a second selection input selecting one or more object features as a second event filter to be combined with the first event filter. The server identifies (1918) at least one motion event from the one or more identified events of interest, where the identified at least one motion event includes at least one object in motion satisfying the one or more object features. The server visually labels (1920) the identified at least one motion event with a respective indicator associated with both the zone of interest and the one or more object features in the event review interface. In some implementations, the one or more object features include features representing a human being, for example, aspect ratio of the object in motion, movement speed of the object in motion, size of the object in motion, shape of the object in motion, etc. The user may select to see all events in which a human being entered a particular zone by selecting the zone and the features associated with a human being in an event reviewing interface. The user may also create combinations of different filters (e.g., zones and/or object features) to create new event filter types.
In some implementations, the definition of the zone of interest includes (1922) a plurality of vertices specified in the scene of the video recording. In some implementations, the user is allowed to create zones of any shapes and sizes by dragging the vertices (e.g., with the dragging gesture in
In some implementations, the server processes (1924) a live video stream depicting the scene of the video recording to detect a start of a live motion event, generates (1926) a live event mask based on respective motion pixels associated with a respective object in motion identified in the live motion event; and determines (1928), in real-time, whether the live event mask overlaps with the zone of interest by at least the predetermined overlap factor. In accordance with a determination that the live event mask overlaps with the zone of interest by at least the predetermined overlap factor, the server generates (1930) a real-time event alert for the zone of interest.
In some implementations, the live event mask is generated based on all past frames in the live motion event that has just been detected. The live event mask is updated as each new frame is received. As soon as an overlap factor determined based on an overlap between the live event mask and the zone of interest exceeds a predetermined threshold, a real-time alert for the event of interest can be generated and sent to the user. In a review interface, the visual indicator, for example, a color, associated with the zone of interest can be applied to the event indicator for the live motion event. For example, a colored boarder may be applied to the event indicator on the timeline, and/or the pop-up notification containing a sprite of the motion event. In some implementations, the server visually labels (1932) the live motion event with a respective indicator associated with the zone of interest in an event review interface.
It should be understood that the particular order in which the operations in
Conventionally, when monitoring a zone of interest within a field of view of a video surveillance system, the system determines whether an object has entered the zone of interest based on the image information within the zone of interest. This is ineffective sometimes when the entire zone of interest is obscured by a moving object, and the details of the motion (e.g., the trajectory and speed of a moving object) are not apparent from merely the image within the zone of interest. For example, such prior art systems are not be able to distinguish a global lighting change from a object moving in front of the camera and consequently obscuring the entire view field of the camera. The technique described herein detects motion events without being constrained by the zones (i.e., boundaries) that have been defined, and then determines if a detected event is of interest based on an overlap factor between the zones and the detected motion events. This allows for more meaningful zone monitoring with context information collected outside of the zones of interest.
As shown in
In some implementations, the server generates (2008) the respective event mask for the motion event, where the generating includes: creating a respective binary motion pixel map for each frame of a respective video segment associated with the motion event; and combining the respective binary motion pixel maps of all frames of the respective video segment to generate the respective event mask for the motion event. Other methods of generating the event mask are described with respect to
In some implementations, the server receives (2010) a first selection input from a user to select the zone of interest as a first event filter. The server receives (2012) a second selection input from the user to select one or more object features as a second event filter to be combined with the first event filter. The server determines (2014) whether the identified event of interest includes at least one object in motion satisfying the one or more object features. The server or a component thereof (e.g., the real-time motion event presentation module 632,
In some implementations, the server visually labels (2018) the identified event of interest with an indicator associated with both the zone of interest and the one or more object features in an event review interface. In some implementations, the one or more object features are (2020) features representing a human. In some implementations, the definition of the zone of interest includes (2022) a plurality of vertices specified in the scene of the video recording.
In some implementations, the video stream is (2024) a live video stream, and determining whether the respective event mask of the motion event overlaps with the zone of interest by at least a predetermined overlap factor further includes: processing the live video stream in real-time to detect a start of a live motion event; generating a live event mask based on respective motion pixels associated with a respective object in motion identified in the live motion event; and determining, in real-time, whether the live event mask overlaps with the zone of interest by at least the predetermined overlap factor.
In some implementations, the server provides (2026) a composite video segment corresponding to the identified event of interest, the composite video segment including a plurality of composite frames each including a high-resolution portion covering the zone of interest, and a low-resolution portion covering regions outside of the zone of interest. For example, the high resolution portion can be cropped from the original video stored in the cloud, and the low resolution region can be a stylized abstraction or down-sampled from the original video.
It should be understood that the particular order in which the operations in
For situations in which the systems discussed above collect information about users, the users may be provided with an opportunity to opt in/out of programs or features that may collect personal information (e.g., information about a user's preferences or usage of a smart device). In addition, in some implementations, certain data may be anonymized in one or more ways before it is stored or used, so that personally identifiable information is removed. For example, a user's identity may be anonymized so that the personally identifiable information cannot be determined for or associated with the user, and so that user preferences or user interactions are generalized (for example, generalized based on user demographics) rather than associated with a particular user.
Although some of various drawings illustrate a number of logical stages in a particular order, stages that are not order dependent may be reordered and other stages may be combined or broken out. While some reordering or other groupings are specifically mentioned, others will be obvious to those of ordinary skill in the art, so the ordering and groupings presented herein are not an exhaustive list of alternatives. Moreover, it should be recognized that the stages could be implemented in hardware, firmware, software or any combination thereof.
The foregoing description, for purpose of explanation, has been described with reference to specific implementations. However, the illustrative discussions above are not intended to be exhaustive or to limit the scope of the claims to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The implementations were chosen in order to best explain the principles underlying the claims and their practical applications, to thereby enable others skilled in the art to best use the implementations with various modifications as are suited to the particular uses contemplated.
This application is a continuation of U.S. application Ser. No. 14/510,029, filed Oct. 8, 2014, entitled “Method and System for Non-Causal Zone Search in Video Monitoring,” which claims priority to U.S. Provisional Patent Application No. 62/057,991, filed Sep. 30, 2014, entitled “Method and System for Video Monitoring,” and U.S. Provisional Patent Application No. 62/021,620, filed Jul. 7, 2014, entitled “Activity Recognition and Video Filtering,” each of which is hereby incorporated by reference in its entirety. This application is related to U.S. Design patent application No. 29/504,605, filed Oct. 7, 2014, entitled “Video Monitoring User Interface with Event Timeline and Display of Multiple Preview Windows At User-Selected Event Marks,” which is hereby incorporated by reference in its entirety.
| Number | Name | Date | Kind |
|---|---|---|---|
| 4198653 | Kamin | Apr 1980 | A |
| 4717847 | Nolan | Jan 1988 | A |
| 4737847 | Araki | Apr 1988 | A |
| 4755870 | Markle et al. | Jul 1988 | A |
| 5237408 | Blum et al. | Aug 1993 | A |
| 5243418 | Kuno | Sep 1993 | A |
| 5396284 | Freeman | Mar 1995 | A |
| 5625410 | Washino et al. | Apr 1997 | A |
| 5627586 | Yamasaki | May 1997 | A |
| 5854902 | Wilson et al. | Dec 1998 | A |
| 5956424 | Wootton et al. | Sep 1999 | A |
| 5969755 | Courtney | Oct 1999 | A |
| 6028626 | Aviv | Feb 2000 | A |
| 6046745 | Moriya et al. | Apr 2000 | A |
| 6104831 | Ruland | Aug 2000 | A |
| 6107918 | Klein et al. | Aug 2000 | A |
| 6130839 | Chang | Oct 2000 | A |
| 6144375 | Jain et al. | Nov 2000 | A |
| 6236395 | Sezan et al. | May 2001 | B1 |
| D450059 | Itou | Nov 2001 | S |
| 6366296 | Boreczky et al. | Apr 2002 | B1 |
| 6400378 | Snook | Jun 2002 | B1 |
| 6424370 | Courtney | Jul 2002 | B1 |
| 6476858 | Ramirez Diaz et al. | Nov 2002 | B1 |
| 6496598 | Harman | Dec 2002 | B1 |
| 6535793 | Allard | Mar 2003 | B2 |
| 6549674 | Chui et al. | Apr 2003 | B1 |
| 6571050 | Park | May 2003 | B1 |
| 6600784 | Divakaran et al. | Jul 2003 | B1 |
| 6611653 | Kim et al. | Aug 2003 | B1 |
| 6628835 | Brill et al. | Sep 2003 | B1 |
| 6643416 | Daniels et al. | Nov 2003 | B1 |
| 6647200 | Tanaka | Nov 2003 | B1 |
| 6665423 | Mehrotra et al. | Dec 2003 | B1 |
| 6680748 | Monti | Jan 2004 | B1 |
| 6697103 | Fernandez et al. | Feb 2004 | B1 |
| 6727938 | Randall | Apr 2004 | B1 |
| 6741977 | Nagaya et al. | May 2004 | B1 |
| D491956 | Ombao et al. | Jun 2004 | S |
| 6792676 | Haji et al. | Sep 2004 | B2 |
| 6816184 | Brill et al. | Nov 2004 | B1 |
| D499740 | Ombao et al. | Dec 2004 | S |
| 6904176 | Chui et al. | Jun 2005 | B1 |
| 6954859 | Simerly | Oct 2005 | B1 |
| 6970183 | Monroe | Nov 2005 | B1 |
| 7016415 | Alvarez | Mar 2006 | B2 |
| 7023469 | Olson | Apr 2006 | B1 |
| 7142600 | Schonfeld et al. | Nov 2006 | B1 |
| D555661 | Kim | Nov 2007 | S |
| 7403116 | Bittner | Jul 2008 | B2 |
| 7421455 | Hua et al. | Sep 2008 | B2 |
| 7421727 | Oya et al. | Sep 2008 | B2 |
| 7433493 | Miyoshi et al. | Oct 2008 | B1 |
| 7440613 | Xu | Oct 2008 | B2 |
| 7447337 | Zhang et al. | Nov 2008 | B2 |
| D590412 | Saft et al. | Apr 2009 | S |
| D607001 | Ording | Dec 2009 | S |
| 7629995 | Salivar et al. | Dec 2009 | B2 |
| 7649938 | Chen et al. | Jan 2010 | B2 |
| 7685519 | Duncan | Mar 2010 | B1 |
| 7760908 | Curtner et al. | Jul 2010 | B2 |
| 7765482 | Wood et al. | Jul 2010 | B2 |
| D621413 | Rasmussen | Aug 2010 | S |
| D625323 | Matsushima et al. | Oct 2010 | S |
| 7813525 | Aggarwal | Oct 2010 | B2 |
| 7823066 | Kuramura | Oct 2010 | B1 |
| 7920626 | Fernandez et al. | Apr 2011 | B2 |
| 7924323 | Walker et al. | Apr 2011 | B2 |
| D638025 | Saft et al. | May 2011 | S |
| 7995096 | Cressy et al. | Aug 2011 | B1 |
| 7996771 | Girgensohn et al. | Aug 2011 | B2 |
| 8115623 | Green | Feb 2012 | B1 |
| 8122038 | Handy et al. | Feb 2012 | B2 |
| 8130839 | Kawashima et al. | Mar 2012 | B2 |
| 8200669 | Iampietro et al. | Jun 2012 | B1 |
| 8204273 | Chambers et al. | Jun 2012 | B2 |
| 8284258 | Cetin et al. | Oct 2012 | B1 |
| 8290038 | Wang et al. | Oct 2012 | B1 |
| 8295597 | Sharma et al. | Oct 2012 | B1 |
| 8300890 | Gaikwad et al. | Oct 2012 | B1 |
| 8305447 | Wong | Nov 2012 | B1 |
| 8305914 | Thielman et al. | Nov 2012 | B2 |
| 8379851 | Mehrotra et al. | Feb 2013 | B2 |
| 8390684 | Piran et al. | Mar 2013 | B2 |
| 8401232 | Fan | Mar 2013 | B2 |
| 8494234 | Bozinovic et al. | Jul 2013 | B1 |
| 8494324 | Ellis | Jul 2013 | B2 |
| 8515128 | Hildreth | Aug 2013 | B1 |
| 8525665 | Trundle et al. | Sep 2013 | B1 |
| 8537219 | Desimone et al. | Sep 2013 | B2 |
| 8577091 | Ivanov et al. | Nov 2013 | B2 |
| 8587653 | Vidunas et al. | Nov 2013 | B1 |
| 8613070 | Borzycki et al. | Dec 2013 | B1 |
| 8639796 | Covell et al. | Jan 2014 | B2 |
| 8676493 | M et al. | Mar 2014 | B2 |
| 8683013 | Major et al. | Mar 2014 | B2 |
| 8688483 | Watts | Apr 2014 | B2 |
| 8707194 | Jenkins et al. | Apr 2014 | B1 |
| 8723955 | Kiehn | May 2014 | B2 |
| 8736680 | Cilia et al. | May 2014 | B1 |
| 8775242 | Tavares et al. | Jul 2014 | B2 |
| 8780201 | Scalisi et al. | Jul 2014 | B1 |
| 8823795 | Scalisi et al. | Sep 2014 | B1 |
| 8854457 | De Vleeschouwer et al. | Oct 2014 | B2 |
| 8902085 | Ray et al. | Dec 2014 | B1 |
| 8922659 | Leny et al. | Dec 2014 | B2 |
| 8941733 | Albers et al. | Jan 2015 | B2 |
| 8941736 | Scalisi | Jan 2015 | B1 |
| 8942438 | Ivanov et al. | Jan 2015 | B2 |
| 8953848 | Ivanov et al. | Feb 2015 | B2 |
| 8958602 | Lane et al. | Feb 2015 | B1 |
| 8966368 | Kuramura | Feb 2015 | B2 |
| 8982141 | Freyhult | Mar 2015 | B2 |
| 9014429 | Badawy | Apr 2015 | B2 |
| 9025836 | Ptucha | May 2015 | B2 |
| 9064393 | He | Jun 2015 | B2 |
| 9082018 | Laska et al. | Jul 2015 | B1 |
| 9124858 | Jang et al. | Sep 2015 | B2 |
| 9158974 | Laska et al. | Oct 2015 | B1 |
| 9170707 | Laska et al. | Oct 2015 | B1 |
| 9172911 | Kristiansen et al. | Oct 2015 | B2 |
| 9213903 | Laska et al. | Dec 2015 | B1 |
| 9269243 | Shet et al. | Feb 2016 | B2 |
| 9307217 | Day | Apr 2016 | B1 |
| 9325905 | Noyes | Apr 2016 | B2 |
| 9361011 | Burns et al. | Jun 2016 | B1 |
| 9420331 | Laska et al. | Aug 2016 | B2 |
| 9449229 | Laska et al. | Sep 2016 | B1 |
| 9479822 | Laska et al. | Oct 2016 | B2 |
| 9489580 | Laska et al. | Nov 2016 | B2 |
| 9516053 | Muddu et al. | Dec 2016 | B1 |
| 9544636 | Laska et al. | Jan 2017 | B2 |
| 9575178 | Kanamori et al. | Feb 2017 | B2 |
| 9582157 | Chatterjee et al. | Feb 2017 | B1 |
| 9584710 | Marman et al. | Feb 2017 | B2 |
| D782495 | Laska et al. | Mar 2017 | S |
| 9600723 | Pantofaru et al. | Mar 2017 | B1 |
| 9602860 | Laska et al. | Mar 2017 | B2 |
| 9609380 | Laska et al. | Mar 2017 | B2 |
| 9613524 | Lamb et al. | Apr 2017 | B1 |
| 9621798 | Zhang et al. | Apr 2017 | B2 |
| 9674453 | Tangeland et al. | Jun 2017 | B1 |
| 9674570 | Laska et al. | Jun 2017 | B2 |
| 9753994 | Anderson | Sep 2017 | B2 |
| 9940523 | Laska et al. | Apr 2018 | B2 |
| 9997053 | Maneskiold et al. | Jun 2018 | B2 |
| 10063815 | Spivey et al. | Aug 2018 | B1 |
| 10108862 | Laska et al. | Oct 2018 | B2 |
| 10127783 | Laska et al. | Nov 2018 | B2 |
| 10140827 | Laska et al. | Nov 2018 | B2 |
| 10180775 | Laska et al. | Jan 2019 | B2 |
| 10192120 | Laska et al. | Jan 2019 | B2 |
| 10289917 | Fu | May 2019 | B1 |
| 10375794 | Wu et al. | Aug 2019 | B2 |
| 10452921 | Laska et al. | Oct 2019 | B2 |
| 10467872 | Laska et al. | Nov 2019 | B2 |
| 10789821 | Laska et al. | Sep 2020 | B2 |
| 10867496 | Laska et al. | Dec 2020 | B2 |
| 20010010541 | Fernandez et al. | Aug 2001 | A1 |
| 20010019631 | Ohsawa et al. | Sep 2001 | A1 |
| 20010024517 | Labelle | Sep 2001 | A1 |
| 20010043721 | Kravets et al. | Nov 2001 | A1 |
| 20010050712 | Dunton et al. | Dec 2001 | A1 |
| 20020002425 | Dossey et al. | Jan 2002 | A1 |
| 20020018072 | Chui | Feb 2002 | A1 |
| 20020021758 | Chui | Feb 2002 | A1 |
| 20020030740 | Arazi et al. | Mar 2002 | A1 |
| 20020054068 | Ellis et al. | May 2002 | A1 |
| 20020054211 | Edelson et al. | May 2002 | A1 |
| 20020089549 | Munro et al. | Jul 2002 | A1 |
| 20020113813 | Yoshimine | Aug 2002 | A1 |
| 20020125435 | Cofer et al. | Sep 2002 | A1 |
| 20020126224 | Lienhart | Sep 2002 | A1 |
| 20020168084 | Trajkovic et al. | Nov 2002 | A1 |
| 20020174367 | Kimmel et al. | Nov 2002 | A1 |
| 20030025599 | Monroe | Feb 2003 | A1 |
| 20030035592 | Cornog et al. | Feb 2003 | A1 |
| 20030040815 | Pavlidis | Feb 2003 | A1 |
| 20030043160 | Elfving et al. | Mar 2003 | A1 |
| 20030053658 | Pavlidis | Mar 2003 | A1 |
| 20030058339 | Trajkovic et al. | Mar 2003 | A1 |
| 20030063093 | Howard | Apr 2003 | A1 |
| 20030095183 | Roberts et al. | May 2003 | A1 |
| 20030103647 | Rui et al. | Jun 2003 | A1 |
| 20030133503 | Paniconi et al. | Jul 2003 | A1 |
| 20030135525 | Huntington et al. | Jul 2003 | A1 |
| 20030142217 | Maehama | Jul 2003 | A1 |
| 20030218696 | Bagga et al. | Nov 2003 | A1 |
| 20040032494 | Ito et al. | Feb 2004 | A1 |
| 20040057715 | Tsuchida | Mar 2004 | A1 |
| 20040060063 | Russ et al. | Mar 2004 | A1 |
| 20040100560 | Stavely et al. | May 2004 | A1 |
| 20040109059 | Kawakita | Jun 2004 | A1 |
| 20040123328 | Coffey et al. | Jun 2004 | A1 |
| 20040125133 | Pea et al. | Jul 2004 | A1 |
| 20040125908 | Cesmeli | Jul 2004 | A1 |
| 20040133647 | Ozkan et al. | Jul 2004 | A1 |
| 20040143602 | Ruiz et al. | Jul 2004 | A1 |
| 20040145658 | Lev-Ran et al. | Jul 2004 | A1 |
| 20040174434 | Walker et al. | Sep 2004 | A1 |
| 20040196369 | Fukasawa et al. | Oct 2004 | A1 |
| 20050005308 | Logan et al. | Jan 2005 | A1 |
| 20050018879 | Ito et al. | Jan 2005 | A1 |
| 20050036658 | Gibbins | Feb 2005 | A1 |
| 20050046699 | Oya | Mar 2005 | A1 |
| 20050047672 | Ben-Ezra et al. | Mar 2005 | A1 |
| 20050074140 | Grasso et al. | Apr 2005 | A1 |
| 20050078868 | Chen et al. | Apr 2005 | A1 |
| 20050104727 | Han | May 2005 | A1 |
| 20050104958 | Egnal et al. | May 2005 | A1 |
| 20050110634 | Salcedo et al. | May 2005 | A1 |
| 20050132414 | Bentley et al. | Jun 2005 | A1 |
| 20050146605 | Lipton et al. | Jul 2005 | A1 |
| 20050151851 | Schnell | Jul 2005 | A1 |
| 20050157949 | Aiso et al. | Jul 2005 | A1 |
| 20050162515 | Venetianer | Jul 2005 | A1 |
| 20050169367 | Venetianer et al. | Aug 2005 | A1 |
| 20050195331 | Sugano | Sep 2005 | A1 |
| 20050207733 | Gargi | Sep 2005 | A1 |
| 20050246119 | Koodali | Nov 2005 | A1 |
| 20060005281 | Shinozaki et al. | Jan 2006 | A1 |
| 20060007051 | Bear et al. | Jan 2006 | A1 |
| 20060028548 | Salivar et al. | Feb 2006 | A1 |
| 20060029363 | Iggulden et al. | Feb 2006 | A1 |
| 20060045185 | Kiryati et al. | Mar 2006 | A1 |
| 20060045354 | Hanna et al. | Mar 2006 | A1 |
| 20060053342 | Bazakos et al. | Mar 2006 | A1 |
| 20060056056 | Ahiska et al. | Mar 2006 | A1 |
| 20060064716 | Sull et al. | Mar 2006 | A1 |
| 20060067585 | Pace | Mar 2006 | A1 |
| 20060070108 | Renkis | Mar 2006 | A1 |
| 20060072014 | Geng | Apr 2006 | A1 |
| 20060072847 | Chor et al. | Apr 2006 | A1 |
| 20060075235 | Renkis | Apr 2006 | A1 |
| 20060093998 | Vertegaal | May 2006 | A1 |
| 20060109341 | Evans | May 2006 | A1 |
| 20060148528 | Jung et al. | Jul 2006 | A1 |
| 20060164561 | Lacy et al. | Jul 2006 | A1 |
| 20060165386 | Garoutte | Jul 2006 | A1 |
| 20060171453 | Rohlfing et al. | Aug 2006 | A1 |
| 20060195716 | Bittner | Aug 2006 | A1 |
| 20060195876 | Calisa | Aug 2006 | A1 |
| 20060227862 | Campbell et al. | Oct 2006 | A1 |
| 20060227997 | Au et al. | Oct 2006 | A1 |
| 20060228015 | Brockway et al. | Oct 2006 | A1 |
| 20060233448 | Pace et al. | Oct 2006 | A1 |
| 20060239645 | Curtner et al. | Oct 2006 | A1 |
| 20060243798 | Kundu et al. | Nov 2006 | A1 |
| 20060285596 | Kondo | Dec 2006 | A1 |
| 20060285843 | Sakurai | Dec 2006 | A1 |
| 20060288288 | Girgensohn et al. | Dec 2006 | A1 |
| 20060291694 | Venetianer et al. | Dec 2006 | A1 |
| 20070002141 | Lipton et al. | Jan 2007 | A1 |
| 20070008099 | Kimmel et al. | Jan 2007 | A1 |
| 20070014554 | Sasaki | Jan 2007 | A1 |
| 20070027365 | Kosted | Feb 2007 | A1 |
| 20070033632 | Baynger et al. | Feb 2007 | A1 |
| 20070035622 | Hanna et al. | Feb 2007 | A1 |
| 20070041727 | Lee et al. | Feb 2007 | A1 |
| 20070058040 | Zhang | Mar 2007 | A1 |
| 20070061862 | Berger et al. | Mar 2007 | A1 |
| 20070086669 | Berger et al. | Apr 2007 | A1 |
| 20070101269 | Hua et al. | May 2007 | A1 |
| 20070127774 | Zhang et al. | Jun 2007 | A1 |
| 20070132558 | Rowe et al. | Jun 2007 | A1 |
| 20070220569 | Ishii | Sep 2007 | A1 |
| 20070223874 | Hentschel | Sep 2007 | A1 |
| 20070255742 | Perez et al. | Nov 2007 | A1 |
| 20070257986 | Ivanov et al. | Nov 2007 | A1 |
| 20070268369 | Amano et al. | Nov 2007 | A1 |
| 20080005269 | Knighton et al. | Jan 2008 | A1 |
| 20080043106 | Hassapis | Feb 2008 | A1 |
| 20080044085 | Yamamoto | Feb 2008 | A1 |
| 20080051648 | Suri et al. | Feb 2008 | A1 |
| 20080071428 | Kim | Mar 2008 | A1 |
| 20080122926 | Zhou et al. | May 2008 | A1 |
| 20080129498 | Howarter et al. | Jun 2008 | A1 |
| 20080170123 | Albertson et al. | Jul 2008 | A1 |
| 20080178069 | Stallings | Jul 2008 | A1 |
| 20080181453 | Xu | Jul 2008 | A1 |
| 20080184245 | St-Jean | Jul 2008 | A1 |
| 20080192129 | Walker et al. | Aug 2008 | A1 |
| 20080225952 | Wang et al. | Sep 2008 | A1 |
| 20080231706 | Connell | Sep 2008 | A1 |
| 20080240579 | Enomoto | Oct 2008 | A1 |
| 20080244453 | Cafer | Oct 2008 | A1 |
| 20080247601 | Ito et al. | Oct 2008 | A1 |
| 20080270363 | Hunt et al. | Oct 2008 | A1 |
| 20080279537 | Doba | Nov 2008 | A1 |
| 20080303903 | Bentley et al. | Dec 2008 | A1 |
| 20080316311 | Albers et al. | Dec 2008 | A1 |
| 20090006368 | Mei et al. | Jan 2009 | A1 |
| 20090010493 | Gornick et al. | Jan 2009 | A1 |
| 20090016599 | Eaton et al. | Jan 2009 | A1 |
| 20090018996 | Hunt et al. | Jan 2009 | A1 |
| 20090033746 | Brown et al. | Feb 2009 | A1 |
| 20090059031 | Miyakoshi | Mar 2009 | A1 |
| 20090060352 | Distante et al. | Mar 2009 | A1 |
| 20090080853 | Chen | Mar 2009 | A1 |
| 20090083787 | Morris | Mar 2009 | A1 |
| 20090100007 | Campbell et al. | Apr 2009 | A1 |
| 20090102924 | Masten, Jr. | Apr 2009 | A1 |
| 20090103622 | Tripathi et al. | Apr 2009 | A1 |
| 20090128632 | Goto et al. | May 2009 | A1 |
| 20090141939 | Chambers et al. | Jun 2009 | A1 |
| 20090154806 | Chang et al. | Jun 2009 | A1 |
| 20090158308 | Weitzenfeld et al. | Jun 2009 | A1 |
| 20090207257 | Jung et al. | Aug 2009 | A1 |
| 20090208181 | Cottrell | Aug 2009 | A1 |
| 20090213937 | Kawase et al. | Aug 2009 | A1 |
| 20090232416 | Murashita | Sep 2009 | A1 |
| 20090244291 | Saptharishi | Oct 2009 | A1 |
| 20090244309 | Maison et al. | Oct 2009 | A1 |
| 20090249247 | Tseng et al. | Oct 2009 | A1 |
| 20090262189 | Marman | Oct 2009 | A1 |
| 20090273711 | Chapdelaine et al. | Nov 2009 | A1 |
| 20090278394 | Itoga | Nov 2009 | A1 |
| 20090278934 | Ecker et al. | Nov 2009 | A1 |
| 20090288011 | Piran et al. | Nov 2009 | A1 |
| 20090292549 | Ma et al. | Nov 2009 | A1 |
| 20090316956 | Higuchi et al. | Dec 2009 | A1 |
| 20090319829 | Takayama | Dec 2009 | A1 |
| 20100002070 | Ahiska | Jan 2010 | A1 |
| 20100002071 | Ahiska | Jan 2010 | A1 |
| 20100002911 | Wu et al. | Jan 2010 | A1 |
| 20100004839 | Yokoyama et al. | Jan 2010 | A1 |
| 20100013943 | Thorn | Jan 2010 | A1 |
| 20100023865 | Fulker et al. | Jan 2010 | A1 |
| 20100026802 | Titus et al. | Feb 2010 | A1 |
| 20100033573 | Malinovski et al. | Feb 2010 | A1 |
| 20100045594 | Jenks et al. | Feb 2010 | A1 |
| 20100060715 | Laasik et al. | Mar 2010 | A1 |
| 20100098165 | Farfade et al. | Apr 2010 | A1 |
| 20100114623 | Bobbitt et al. | May 2010 | A1 |
| 20100128927 | Ikenoue | May 2010 | A1 |
| 20100133008 | Gawski et al. | Jun 2010 | A1 |
| 20100141763 | Itoh et al. | Jun 2010 | A1 |
| 20100162114 | Roth | Jun 2010 | A1 |
| 20100166260 | Huang et al. | Jul 2010 | A1 |
| 20100192212 | Raleigh | Jul 2010 | A1 |
| 20100201815 | Anderson et al. | Aug 2010 | A1 |
| 20100205203 | Anderson | Aug 2010 | A1 |
| 20100210240 | Mahaffey et al. | Aug 2010 | A1 |
| 20100245107 | Fulker et al. | Sep 2010 | A1 |
| 20100288468 | Patel et al. | Nov 2010 | A1 |
| 20100290668 | Friedman et al. | Nov 2010 | A1 |
| 20100304731 | Bratton et al. | Dec 2010 | A1 |
| 20110001605 | Kiani et al. | Jan 2011 | A1 |
| 20110035054 | Gal et al. | Feb 2011 | A1 |
| 20110050901 | Oya | Mar 2011 | A1 |
| 20110051808 | Quast et al. | Mar 2011 | A1 |
| 20110058708 | Ikenoue | Mar 2011 | A1 |
| 20110063462 | Koike | Mar 2011 | A1 |
| 20110069175 | Mistretta et al. | Mar 2011 | A1 |
| 20110107364 | Lajoie et al. | May 2011 | A1 |
| 20110149078 | Fan | Jun 2011 | A1 |
| 20110157358 | Bell | Jun 2011 | A1 |
| 20110167369 | Van Os | Jul 2011 | A1 |
| 20110173235 | Aman et al. | Jul 2011 | A1 |
| 20110176043 | Baker et al. | Jul 2011 | A1 |
| 20110187290 | Krause | Aug 2011 | A1 |
| 20110199488 | Gorilovskij et al. | Aug 2011 | A1 |
| 20110199535 | Isu et al. | Aug 2011 | A1 |
| 20110211563 | Herrala et al. | Sep 2011 | A1 |
| 20110231428 | Kuramura | Sep 2011 | A1 |
| 20110235998 | Pond et al. | Sep 2011 | A1 |
| 20110254950 | Bibby et al. | Oct 2011 | A1 |
| 20110254972 | Yaguchi | Oct 2011 | A1 |
| 20110255741 | Jung et al. | Oct 2011 | A1 |
| 20110255775 | McNamer et al. | Oct 2011 | A1 |
| 20110276710 | Mighani et al. | Nov 2011 | A1 |
| 20110276881 | Keng et al. | Nov 2011 | A1 |
| 20110291925 | Israel | Dec 2011 | A1 |
| 20110300933 | Chien et al. | Dec 2011 | A1 |
| 20110312350 | Agerholm | Dec 2011 | A1 |
| 20120005628 | Isozu et al. | Jan 2012 | A1 |
| 20120011567 | Cronk et al. | Jan 2012 | A1 |
| 20120019728 | Moore | Jan 2012 | A1 |
| 20120045090 | Bobbitt et al. | Feb 2012 | A1 |
| 20120052972 | Bentley et al. | Mar 2012 | A1 |
| 20120098918 | Murphy | Apr 2012 | A1 |
| 20120120238 | Adar et al. | May 2012 | A1 |
| 20120121187 | Lee et al. | May 2012 | A1 |
| 20120169842 | Chuang et al. | Jul 2012 | A1 |
| 20120173577 | Millar et al. | Jul 2012 | A1 |
| 20120176496 | Carbonell et al. | Jul 2012 | A1 |
| 20120195363 | Laganiere et al. | Aug 2012 | A1 |
| 20120198319 | Agnoli et al. | Aug 2012 | A1 |
| 20120200762 | Nakano | Aug 2012 | A1 |
| 20120216296 | Kidron | Aug 2012 | A1 |
| 20120257000 | Singhal | Oct 2012 | A1 |
| 20120319592 | Riesebosch | Dec 2012 | A1 |
| 20120327250 | Zhang et al. | Dec 2012 | A1 |
| 20130016122 | Bhatt | Jan 2013 | A1 |
| 20130027581 | Price et al. | Jan 2013 | A1 |
| 20130076908 | Bratton et al. | Mar 2013 | A1 |
| 20130083198 | Maslan | Apr 2013 | A1 |
| 20130086665 | Filippi et al. | Apr 2013 | A1 |
| 20130089301 | Ju | Apr 2013 | A1 |
| 20130125039 | Murata | May 2013 | A1 |
| 20130128022 | Bose | May 2013 | A1 |
| 20130135509 | Fuji | May 2013 | A1 |
| 20130145270 | Piran et al. | Jun 2013 | A1 |
| 20130163430 | Gell et al. | Jun 2013 | A1 |
| 20130176430 | Zhu et al. | Jul 2013 | A1 |
| 20130182905 | Myers et al. | Jul 2013 | A1 |
| 20130194447 | Sudo | Aug 2013 | A1 |
| 20130201329 | Thornton et al. | Aug 2013 | A1 |
| 20130202210 | Ryoo et al. | Aug 2013 | A1 |
| 20130242093 | Cobb et al. | Sep 2013 | A1 |
| 20130243322 | Noh et al. | Sep 2013 | A1 |
| 20130266292 | Sandrew et al. | Oct 2013 | A1 |
| 20130268357 | Heath | Oct 2013 | A1 |
| 20130276140 | Coffing et al. | Oct 2013 | A1 |
| 20130279810 | Li et al. | Oct 2013 | A1 |
| 20130279884 | Gifford | Oct 2013 | A1 |
| 20130320862 | Campbell et al. | Dec 2013 | A1 |
| 20130340050 | Harrison | Dec 2013 | A1 |
| 20130342689 | Sanjay et al. | Dec 2013 | A1 |
| 20140007222 | Qureshi et al. | Jan 2014 | A1 |
| 20140009671 | Ozone | Jan 2014 | A1 |
| 20140013243 | Flynn, III | Jan 2014 | A1 |
| 20140022432 | Goto | Jan 2014 | A1 |
| 20140043534 | Nakaoka | Feb 2014 | A1 |
| 20140044404 | Grundmann et al. | Feb 2014 | A1 |
| 20140049656 | Kimoto | Feb 2014 | A1 |
| 20140050406 | Buehler et al. | Feb 2014 | A1 |
| 20140053200 | de Paz et al. | Feb 2014 | A1 |
| 20140055610 | Ko et al. | Feb 2014 | A1 |
| 20140056479 | Bobbitt et al. | Feb 2014 | A1 |
| 20140063229 | Olsson et al. | Mar 2014 | A1 |
| 20140068349 | Scott et al. | Mar 2014 | A1 |
| 20140068705 | Chambers et al. | Mar 2014 | A1 |
| 20140068789 | Watts et al. | Mar 2014 | A1 |
| 20140075370 | Guerin et al. | Mar 2014 | A1 |
| 20140075382 | Cheng | Mar 2014 | A1 |
| 20140082497 | Chalouhi et al. | Mar 2014 | A1 |
| 20140098992 | Yagi et al. | Apr 2014 | A1 |
| 20140105564 | Johar | Apr 2014 | A1 |
| 20140129942 | Rathod | May 2014 | A1 |
| 20140137153 | Fay et al. | May 2014 | A1 |
| 20140137188 | Bartholomay et al. | May 2014 | A1 |
| 20140142907 | Gellaboina et al. | May 2014 | A1 |
| 20140143695 | Sundermeyer et al. | May 2014 | A1 |
| 20140146125 | Kristiansen et al. | May 2014 | A1 |
| 20140157370 | Plattner et al. | Jun 2014 | A1 |
| 20140160294 | Naylor | Jun 2014 | A1 |
| 20140173692 | Srinivasan et al. | Jun 2014 | A1 |
| 20140189808 | Mahaffey et al. | Jul 2014 | A1 |
| 20140195952 | Champagne et al. | Jul 2014 | A1 |
| 20140198237 | Noyes | Jul 2014 | A1 |
| 20140201761 | Dalal et al. | Jul 2014 | A1 |
| 20140204207 | Clark et al. | Jul 2014 | A1 |
| 20140210646 | Subramanya | Jul 2014 | A1 |
| 20140219088 | Oyman et al. | Aug 2014 | A1 |
| 20140229604 | Pfeffer | Aug 2014 | A1 |
| 20140245411 | Meng et al. | Aug 2014 | A1 |
| 20140245461 | O'Neill et al. | Aug 2014 | A1 |
| 20140253667 | Tian | Sep 2014 | A1 |
| 20140254863 | Marks et al. | Sep 2014 | A1 |
| 20140265882 | Laski et al. | Sep 2014 | A1 |
| 20140267821 | Masuura | Sep 2014 | A1 |
| 20140282877 | Mahaffey et al. | Sep 2014 | A1 |
| 20140285705 | Uchida | Sep 2014 | A1 |
| 20140289376 | Chan et al. | Sep 2014 | A1 |
| 20140300722 | Garcia | Oct 2014 | A1 |
| 20140313142 | Yairi | Oct 2014 | A1 |
| 20140313316 | Olsson et al. | Oct 2014 | A1 |
| 20140313542 | Benchorin et al. | Oct 2014 | A1 |
| 20140320740 | Wan et al. | Oct 2014 | A1 |
| 20140333775 | Naikal et al. | Nov 2014 | A1 |
| 20140339374 | Mian et al. | Nov 2014 | A1 |
| 20140347475 | Divakaran et al. | Nov 2014 | A1 |
| 20140362225 | Ramalingamoorthy et al. | Dec 2014 | A1 |
| 20140376876 | Bentley et al. | Dec 2014 | A1 |
| 20150020014 | Suzuki et al. | Jan 2015 | A1 |
| 20150022432 | Stewart | Jan 2015 | A1 |
| 20150022660 | Kavadeles | Jan 2015 | A1 |
| 20150042570 | Lombardi et al. | Feb 2015 | A1 |
| 20150046184 | Cocco et al. | Feb 2015 | A1 |
| 20150052029 | Wu et al. | Feb 2015 | A1 |
| 20150054949 | Scalisi | Feb 2015 | A1 |
| 20150054981 | Saiki et al. | Feb 2015 | A1 |
| 20150074535 | Silberstein et al. | Mar 2015 | A1 |
| 20150098613 | Gagvani | Apr 2015 | A1 |
| 20150147049 | Eronen et al. | May 2015 | A1 |
| 20150181088 | Wu et al. | Jun 2015 | A1 |
| 20150194134 | Dureau et al. | Jul 2015 | A1 |
| 20150201152 | Cho et al. | Jul 2015 | A1 |
| 20150201198 | Marlatt | Jul 2015 | A1 |
| 20150215586 | Lasko | Jul 2015 | A1 |
| 20150234571 | Lee et al. | Aug 2015 | A1 |
| 20150235551 | Maneskiold et al. | Aug 2015 | A1 |
| 20150242687 | Seo | Aug 2015 | A1 |
| 20150242994 | Shen | Aug 2015 | A1 |
| 20150279182 | Kanaujia et al. | Oct 2015 | A1 |
| 20150281622 | Fujihashi | Oct 2015 | A1 |
| 20150296589 | Melanson et al. | Oct 2015 | A1 |
| 20150310794 | Glue et al. | Oct 2015 | A1 |
| 20150339702 | Lin et al. | Nov 2015 | A1 |
| 20150341599 | Carey | Nov 2015 | A1 |
| 20160005281 | Laska et al. | Jan 2016 | A1 |
| 20160006932 | Zhang et al. | Jan 2016 | A1 |
| 20160006988 | Zhao | Jan 2016 | A1 |
| 20160026862 | Anderson | Jan 2016 | A1 |
| 20160041724 | Kirkby et al. | Feb 2016 | A1 |
| 20160042621 | Hogg | Feb 2016 | A1 |
| 20160072831 | Rieke | Mar 2016 | A1 |
| 20160092737 | Laska et al. | Mar 2016 | A1 |
| 20160092738 | Laska et al. | Mar 2016 | A1 |
| 20160103559 | Maheshwari et al. | Apr 2016 | A1 |
| 20160103887 | Fletcher et al. | Apr 2016 | A1 |
| 20160110612 | Sabripour | Apr 2016 | A1 |
| 20160117951 | Fleisher et al. | Apr 2016 | A1 |
| 20160140697 | Sugimoto | May 2016 | A1 |
| 20160189531 | Modi | Jun 2016 | A1 |
| 20160195716 | Nakanuma | Jul 2016 | A1 |
| 20160219248 | Reznik et al. | Jul 2016 | A1 |
| 20160235344 | Auerbach | Aug 2016 | A1 |
| 20160241818 | Palanisamy et al. | Aug 2016 | A1 |
| 20160274771 | Seong et al. | Sep 2016 | A1 |
| 20160277474 | Ljung et al. | Sep 2016 | A1 |
| 20160285724 | Lundquist et al. | Sep 2016 | A1 |
| 20160307418 | Pantus | Oct 2016 | A1 |
| 20160316176 | Laska et al. | Oct 2016 | A1 |
| 20160316256 | Laska et al. | Oct 2016 | A1 |
| 20160321889 | Gagvani | Nov 2016 | A1 |
| 20160360116 | Penha et al. | Dec 2016 | A1 |
| 20160364966 | Dixon | Dec 2016 | A1 |
| 20160366036 | Gupta et al. | Dec 2016 | A1 |
| 20170019605 | Ahiska | Jan 2017 | A1 |
| 20170039729 | Wang et al. | Feb 2017 | A1 |
| 20170111494 | Kidron et al. | Apr 2017 | A1 |
| 20170123492 | Marggraff et al. | May 2017 | A1 |
| 20170124821 | Zhang | May 2017 | A1 |
| 20170162230 | Maliuk et al. | Jun 2017 | A1 |
| 20170163929 | Maliuk et al. | Jun 2017 | A1 |
| 20170180678 | Fish et al. | Jun 2017 | A1 |
| 20170257612 | Emeott et al. | Sep 2017 | A1 |
| 20180004784 | Tompkins | Jan 2018 | A1 |
| 20180089328 | Bath et al. | Mar 2018 | A1 |
| 20180096197 | Kephart | Apr 2018 | A1 |
| 20180114531 | Kumar et al. | Apr 2018 | A1 |
| 20180121035 | Filippi et al. | May 2018 | A1 |
| 20180139254 | Oyman et al. | May 2018 | A1 |
| 20180144314 | Miller | May 2018 | A1 |
| 20180182148 | Yanagisawa | Jun 2018 | A1 |
| 20180218053 | Koneru | Aug 2018 | A1 |
| 20180219897 | Muddu et al. | Aug 2018 | A1 |
| 20180324399 | Spears | Nov 2018 | A1 |
| 20190004639 | Faulkner | Jan 2019 | A1 |
| 20190035241 | Laska et al. | Jan 2019 | A1 |
| 20190066473 | Laska et al. | Feb 2019 | A1 |
| 20190096206 | Nakagawa | Mar 2019 | A1 |
| 20190156126 | Laska et al. | May 2019 | A1 |
| 20190311201 | Selinger | Oct 2019 | A1 |
| 20200143645 | Laska et al. | May 2020 | A1 |
| Number | Date | Country |
|---|---|---|
| 1024666 | Aug 2000 | EP |
| 2390853 | Nov 2011 | EP |
| 2557784 | Feb 2013 | EP |
| WO 2009138037 | Nov 2009 | WO |
| 2014044643 | Mar 2014 | WO |
| Entry |
|---|
| N. Hueber, C. Hennequin, P. Raymond, &J.P. Moeglin, “Real-time movement detection and analysis for video surveillance applications”, 9079 Proc. SPIE 0B-1-0B-7 (Jun. 10, 2014) (Year: 2014). |
| Google LLC, EP Patent Certificate, EP Patent No. 3022720, Jan. 21, 2018, 1 pg. |
| Central Intelligence Agency “Words of Estimative Probability” May 25, 2018, 12 pgs. |
| Birk, Deterministic Load-Balancing Schemes for Disk-Based Video-on-Demand Storage Servers, 14 IEEE Symposium on Mass Storage Systems, Sep. 1995, pp. 17-25. |
| Castellanos, Event Detection in Video Using Motion Analysis, 1st ACM Int'l Workshop on Analysis & Retrieval of Tracked Events & Motion in Imagery Streams, Oct. 2010, pp. 57-62. |
| D. D Buzan, S. Sclaroff, & G. Kollios, “Extraction and clustering of motion trajectories in video”, 2 Proceedings of the 17th Intl Conf. on Pattern Recognition 521-524 (Aug. 2004). |
| Delbruck, Frame-free dynamic digital vision, 2008 Int'l Symp. On Secure-Life Electronics, Advanced Electronics for Quality Life & Socy, Mar. 2008, pp. 21-26. |
| Ellis, Model-based vision for automatic alarm interpretation, IEEE 1990 Int'l Camahan Conf. on Security Tech, Oct. 1990, pp. 62-67. |
| FI8921W email notification and motion alarm, Jun. 4, 2013, pp. 1-4, http://foscam.us/forum/fi8921w-email-notification-and-motion-alarm-t5874.html. |
| Google Google Inc., International Search Report and Written Opinion, PCT/US2015/039425, dated Sep. 28, 2015, 12 pgs. |
| Gresham, Review: iZon wi-fi Video monitor and its companion iOS app, 2012, p. 1-8, wvvw.idownloadblog.com/2012/11/21/stem-izon-review. |
| Halliquist, How do I set up Activity Alerts, 2013, p. 1-3, http://support.dropcam.com/entries/27880086-How-do-i-set-up-Activity-Alerts. |
| ISPY, Motion Detection Setting up Motion Detection, Dec. 11, 2011, pp. 1-3, https://www.ispyconnect.com/userguide-motion-detection.aspx. |
| IZON App Guide, 2014, p. 1-30, www.isoncam.com/wp-content/uploads/2014/06/IZON-App-Guide.pdf. |
| James Drinkwater, “HOWTO: Set up motion detection in a Mobotix network camera”, http://www.networkwebcams.com/ip-camera-learning-center/2010/03/03/howto-setting-up-motion-detection-in-a-mobotix-camera/, Mar. 3, 2010. |
| L. L Zelnik-Manor, “Event-based analysis of video”, 2 Proceedings of the 2001 IEEE Computer Soc'y Conf. on Computer Vision & Pattern Recognition 123-130 (2001). |
| Logitech, Logitech Alert Video Security System: Getting to Know, 2010, p. 1-9, www.logitech.com/assets/32688/good-to-know.pdf. |
| Medioni, Event detection and analysis from video streams, 23 IEEE Transactions on Pattern Analysis & Machine Intelligence, Aug. 2001, pp. 873-889. |
| Revis, How to Setup Motion Detection of your D-Link Camera, Apr. 9, 2014, pp. 1-8, http://blog.dlink.com/how-to-set-up-motion-detection-on-your-d-link-camera. |
| Schraml, A spatio-termporal clustering method using real-time motion analysis on event-based 3D vision, 2010 IEEE Comp. Socy Conf. on Comp. Vision & Pattern Recognition Workshops, Jun. 2010, pp. 57-63. |
| Shim, A Study of Surveillance System of Objects Abnormal Behaviour by Blob Composition Analysis, 8 Int'l J. of Security & Its Applications, Mar. 2014, pp. 333-340. |
| Yoon, Event Detection from MPEG Video in the Compressed Domain, 15th Int'l Conf. on Pattern Recognition, Sep. 2000, pp. 819-822. |
| You Tube, Sky News Live (screenshot of website illustrating live stream video with timeline having preview thumbnail of past images within the stream), accessed Mar. 23, 2016, 2 pgs, www.youtube.com/watch?v=y60wDzZt8yg. |
| L. Li, W. Whuang, I.Y.H. Gu, & Q. Tian, “Statistical Modeling of Complex Backgrounds for Foreground Object Detection”, 13 IEEE Transactions on Image Processing 1459-1472 (Nov. 2004). |
| M. Camplani, T. Mantecon, & L. Salgado, “Accurate Depth-Color Scene Modeling for 3D Contents Generation with Low Cost Depth Cameras”, 19 IEEE Int'l Conf. on Image Processing 1741-1744 (Oct. 2012). |
| F. Zhou, F. De la Torre, & J.K. Hodgins, “Aligned Cluster Analysis for Temporal Segmentation of Human Motion”, 8 IEEE Int'l Conf. on Automatic Face & Gesture Recognition 1-7 (Sep. 2008). |
| Yuri Ivanov and Christopher Wren, “Toward Spatial Queries for Spatial Surveillance Tasks”, May 2006, https://www. researchaate.netlprofile/Yuri 1van0v2/publication/21 5439735 Toward Spatial Queries for Spatial Surveillance T asks/links/0c960539e6408cb328000000.pdf, p. 1-9. |
| Author Unknown, “Ch. 1 Configuring Main System” (GEOVision), 2009, https://web.archive.org/web/20090520185506/https:/videos.cctvcamerapros.com/pdf/geovision/geovision-8-manual-chl.pdf, p. 1-79. |
| Prosecution History from U.S. Appl. No. 14/510,029, dated Feb. 9, 2015 through Jul. 14, 2017, 92 pp. |
| Graph Maker, [online], graphs uploaded on Oct. 26, 2013 & Oct. 27, 2013 & Nov. 17, 2013, retrieved on Dec. 20, 2018. Retrieved from, <URL : https://forunn.unity.conn/threads/released-graph-nnaker-ugui-ngui-dfgui-line-graphs-bar-graphs-pie-graphs-etc.202437/>, all pages. |
| Amplification of the Antibody Response, [online], published on Mar. 15, 1999, retrieved on Dec. 20, 2018. Retrieved from, <URL: http://www.jimmunol.org/content/162/6/3647>, all pages. |
| Histograms, [online], publication date unknown, retrieved on Dec. 20, 2018. Retrieved from, <URL: https://root.cern.ch/root/htmldoc/ guides/users-guide/Histograms.html>, all pages. |
| File:savedemo.png, [online], graph uploaded on Apr. 3, 2014, retrieved on Dec. 20, 2018. Retrieved from, <URL: http://wiki.freepascal.org/File:savedenno.png>, all pages. |
| Literature Review—Graphical Tools, [online], publication date unknown, retrieved on Dec. 20, 2018. Retrieved from <URL: https://www.stat.auckland.ac.nz/-joh024/LitReviews/LitReview. GraphicalTools.pdf>, all pages. |
| Clustered/Stacked Filled Bar Graph Generator, [online], website crawled on Mar. 26, 2014, retrieved on Dec. 31, 2018. Retrieved from, < URL: https://web.archive.org/web/20140326054333/http://www.burningcutlery.conn:80/derek/bargraph/>, all pages. |
| Number | Date | Country | |
|---|---|---|---|
| 20180012077 A1 | Jan 2018 | US |
| Number | Date | Country | |
|---|---|---|---|
| 62057991 | Sep 2014 | US | |
| 62021620 | Jul 2014 | US |
| Number | Date | Country | |
|---|---|---|---|
| Parent | 14510029 | Oct 2014 | US |
| Child | 15712039 | US |
