System and method for auditing the fill status of a customer waste container by a waste services provider during performance of a waste service activity

Information

  • Patent Grant
  • 11475417
  • Patent Number
    11,475,417
  • Date Filed
    Thursday, January 9, 2020
    4 years ago
  • Date Issued
    Tuesday, October 18, 2022
    a year ago
Abstract
Systems and methods are provided for using video/still images captured by continuously recording optical sensors mounted on waste collection vehicles used in in the waste collection, disposal and recycling industry for operational and customer service related purposes. A system is provided for auditing the fill status of a customer waste container by a waste services provider during performance of a waste service activity.
Description
BACKGROUND
1. Field of the Invention

The presently disclosed subject matter relates to waste management, and more particularly, to a waste management system for auditing a fill status of a customer waste container by a waste services provider during performance of a waste service activity.


2. Description of the Related Art

Waste service vehicles and waste container delivery vehicles used in the waste collection, disposal and recycling industry often have on-board computers, location devices and interior and exterior safety and non-safety related cameras installed on the exterior and interior thereof. These systems can provide waste services providers and their field managers with information related to the waste service vehicle, location of the waste service vehicle, waste service confirmation, customer service issues, service routing issues, customer site information and safety issues and concerns.


A common concern for waste services providers is overloaded customer containers.


Containers with trash or recyclables protruding from the top or sides can result in scattered contents and possible injury or accidents. Waste services providers have sought improved means for identifying and addressing and/or preventing overloaded containers. Waste services providers have also sought improved means for auditing the status of customer waste containers, including but not limited to the container fill status, during performance of a waste service activity.


Prior auditing means were typically performed visually by the driver or other employees at the site of the customer waste container, and were often inefficient and/or provided inaccurate results.


Improvements in this field of technology are desired.


SUMMARY

Various illustrative embodiments of a system for auditing the fill status of a customer waste container by a waste services provider during performance of a waste service activity are disclosed herein.


In certain aspects, the system can include an optical sensor disposed on a waste collection vehicle and configured to capture image data of the customer waste container that is indicative of the fill status of the container. The system can also include a memory storage area and a processor in communication with the memory storage area. The processor can be configured to, in real time during performance of the waste service activity: receive the image data from the optical sensor; compare the fill status from the image data to a predetermined overload threshold condition for the customer waste container stored in the memory storage area; determine, based on the comparison, whether the fill status has met or exceeded the predetermined overload threshold condition; if the fill status has met or surpassed the predetermined overload threshold condition, generate an action proposal; and execute an action from the action proposal, wherein the action can comprise one or more of: (i) a customer communication, (ii) a customer billing adjustment, and (iii) a container recovery instruction for the customer waste container for delivery to the waste collection vehicle. The comparing and determining can be performed using machine learning based on programmed data associated with recognition of the fill status. The container recovery instruction for the customer waste container for delivery to the waste collection vehicle can include an instruction to collect the customer waste container and deliver it to the waste collection vehicle for removal from the customer location. The processor can be configured to identify the location of the waste collection vehicle and associate the location of the waste collection vehicle with the identity of the specific customer at that location. The steps of identifying and associating can performed prior to receiving the image data from the optical sensor, or performed subsequent to receiving the image data from the optical sensor.


Various illustrative embodiments of a method for auditing the fill status of a customer waste container by a waste service provider during performance of a waste service activity are also disclosed herein.


In certain aspects, the method can include certain of the following steps: capturing image data of the customer waste container that is indicative of the fill status of the container; comparing the fill status from the image data to a predetermined overload threshold condition for the customer waste container; determining, based on the comparison, whether the fill status has met or exceeded the predetermined overload threshold condition; if the fill status has met or surpassed the predetermined overload threshold condition, generating an action proposal; and executing an action from the action proposal, wherein the action comprises one or more of: a customer communication, a customer billing adjustment, and a container recovery instruction for the customer waste container for delivery to the waste collection vehicle.





BRIEF DESCRIPTION OF THE DRAWINGS

A better understanding of the presently disclosed subject matter can be obtained when the following detailed description is considered in conjunction with the drawings and figures herein, wherein:



FIG. 1 is a representative example of a waste services environment where a waste service vehicle is configured to capture images from vehicle mounted optical sensors of customer waste containers and other service related and non-service related activity outside of the waste service vehicle in accordance with an illustrative embodiment of the presently disclosed subject matter;



FIG. 2 is a system for auditing a status of a customer waste container by a waste services provider during performance of a waste service activity in the environment of FIG. 1, in accordance with an illustrative embodiment of the presently disclosed subject matter;



FIG. 3A is an example of a communications network in accordance with an illustrative embodiment of the presently disclosed subject matter;



FIG. 3B is an example of a communications network for a waste services vehicle in accordance with an illustrative embodiment of the presently disclosed subject matter;



FIG. 4 is an example of a computing system in accordance with an illustrative embodiment of the presently disclosed subject matter;



FIG. 5 is a flowchart for auditing the container fill status of a customer waste container during performance of a waste service activity in accordance with an illustrative embodiment of the presently disclosed subject matter;



FIG. 6 is a flowchart for auditing the container fill status of a customer waste container during performance of a waste service activity in accordance with an illustrative embodiment of the presently disclosed subject matter;



FIG. 7 is a flowchart for auditing the container fill status of a customer waste container during performance of a waste service activity in accordance with an illustrative embodiment of the presently disclosed subject matter;



FIG. 8 is a flowchart for auditing the container fill status of a customer waste container during performance of a waste service activity in accordance with an illustrative embodiment of the presently disclosed subject matter; and



FIG. 9 is an illustration of a fill status from image data being compared to a predetermined overload threshold condition for a customer waste container in accordance with an illustrative embodiment of the presently disclosed subject matter.





While the presently disclosed subject matter will be described in connection with the preferred embodiment, it will be understood that it is not intended to limit the presently disclosed subject matter to that embodiment. On the contrary, it is intended to cover all alternatives, modifications, and equivalents, as may be included within the spirit and the scope of the presently disclosed subject matter as defined by the appended claims.


DETAILED DESCRIPTION

The presently disclosed subject matter relates to systems and methods for auditing the status of a customer waste container by a waste services provider using video/still images captured by one or more optical sensors mounted on a waste collection vehicle used in the waste collection, disposal and recycling industry. The presently disclosed systems and methods are directed to overcoming the issues and problems of the prior art.



FIG. 1 is an example of a waste services environment 10 where the presently disclosed system and method can be utilized. A waste service vehicle 15 is configured to provide services to customers, which can include typical lines of waste industry services such as waste collection and transport and/or recycling for commercial, residential and/or industrial. Waste service vehicle 15 collects waste or recyclables from a plurality of containers 20 which will typically be assigned to, or associated with, specific customers registered to a waste collection company.



FIG. 2 illustrates a high-level overview of a system and network according to various illustrative embodiments herein. The components and general architecture of the system and network may be adapted for use in the specific waste services environment of FIG. 1. The system can include one or more data sources 30 and a central server 35. Data sources 30 may be, for example, devices configured for capturing and communicating operational data indicative of one or more operational characteristics (e.g., one or more optical sensors 40 on waste service vehicle 15 capturing video or still images of containers 20). Data sources 30 are configured to communicate with central server 35 by sending and receiving operational data over a network 45 (e.g., the Internet, an Intranet, or other suitable network). Central server 35 may be configured to process and evaluate operational data received from data sources 30 in accordance with user input received via a user interface provided on a local or remote computer.


In the illustrative embodiment shown in FIGS. 3A, 3B and 4, a system and network are shown wherein a communications device 50 can be disposed on waste service vehicle 15. Communications device 50 and central server 35 are configured to communicate with each other via a communications network 45 (e.g., the Internet, an Intranet, a cellular network, or other suitable network). In addition, communications device 50 and central server 35 are configured for storing data to an accessible central server database 96 located on, or remotely from, central server 35. In the description provided herein, the system may be configured for managing and evaluating the operation of a large fleet of waste service vehicles 15. As such, in certain illustrative embodiments, the system may further comprise a plurality of communications devices 50, each being associated with one of a plurality of waste service vehicles 15.


In certain illustrative embodiments, the communication between communications device 50 provided on-board waste service vehicle 15 and central server 35 may be provided on a real time basis such that during the collection route, data is transmitted from each waste service vehicle 15 to central server 35. Alternatively, communication device 50 may be configured to temporarily store or cache data during the collection route and transfer the data to the central server 35 on return of waste service vehicle 15 to the location of the waste collection company.


In certain illustrative embodiments, as illustrated in FIG. 3B, waste service vehicle 15 can also include an onboard computer 60, a location device 65, and an optical sensor 70. Onboard computer 60 can be, for example, a standard desktop or laptop personal computer (“PC”), or a computing apparatus that is physically integrated with vehicle 15, and can include and/or utilize various standard interfaces that can be used to communicate with location device 65 and optical sensor 70. Onboard computer 60 can also communicate with central server 35 via a communications network 45 via communication device 50.


Location device 65 can be configured to determine the location of waste service vehicle 15 always while waste service vehicle 15 is inactive, in motion and operating and performing service related and nonservice related activities. For example, location device 65 can be a GPS device that can communicate with the waste collection company. A satellite 75 or other communications device can be utilized to facilitate communications. For example, location device 65 can transmit location information, such as digital latitude and longitude, to onboard computer 60 via satellite 75. Thus, location device 65 can identify the location of waste service vehicle 15, and therefore the location of the customer site where container 20 is located, after vehicle 15 has arrived at the customer site.


In certain illustrative embodiments, optical sensor 70 can be configured to capture still or video images of containers 20 as well as other service related and non-service related activity outside of the waste service vehicle 15. Optical sensor 70 can be, for example, a video camera. Optical sensor 70 can be disposed on waste collection vehicle 15 and configured to capture image data of customer waste container 20 that is indicative of the fill status of container 20. The images collected by optical sensor 70 may be transmitted to and stored by onboard computer 60, and/or delivered to central server 35.


For example, in certain illustrative embodiments one or more optical sensors 70 can be installed throughout the waste collection vehicle 15 including, but not limited to, high definition cameras, monitors and such other sensors mounted to the front (interior and exterior of the cab), exterior right side, exterior left side, exterior rear and exterior/interior hopper area of the service vehicle. Optical sensor 70 can periodically or continuously record, or record upon demand, desired activities outside the vehicle 15. The recorded images and data can be stored on onboard computer 60 using a recording device (such as a digital video recorder) and be also be transmitted and stored remotely away from waste service vehicle 15 or in the “cloud” via cellular and/or other wireless transmissions and/or communicate vis network 45. The images can be available for review in immediate real-time or passive review later by an end-user.


In the illustrative embodiment of FIG. 4, a exemplary computer system and associated communication network is shown. In certain illustrative embodiments, central server 35 can be configured to receive and store operational data (e.g., data received from waste services vehicle 15) and evaluate the data to aid waste services company in improving operational efficiency. Central server 35 can include various means for performing one or more functions in accordance with embodiments of the present invention, including those more particularly shown and described herein; however, central server 35 may include alternative devices for performing one or more like functions without departing from the spirit and scope of the present invention.


In certain illustrative embodiments, central server 35 can include standard components such as processor 75 and user interface 80 for inputting and displaying data, such as a keyboard and mouse or a touch screen, associated with a standard laptop or desktop computer. Central server 35 also includes a communication device 85 for wireless communication with onboard computer 60.


Central server 35 may include software 90 that communicates with one or more memory storage areas 95. Memory storage areas 95 can be, for example, multiple data repositories which stores pre-recorded data pertaining to a plurality of customer accounts. Such information may include customer location, route data, items expected to be removed from the customer site, and/or billing data. For example, using the location (e.g., street address, city, state, and zip code) of a customer site, software 90 may find the corresponding customer account in memory storage areas 95. Database 96 for data storage can be in memory storage area 95 and/or supplementary external storage devices as are well known in the art.


While a “central server” is described herein, a person of ordinary skill in the art will recognize that embodiments of the present invention are not limited to a client-server architecture and that the server need not be centralized or limited to a single server, or similar network entity or mainframe computer system. Rather, the server and computing system described herein may refer to any combination of devices or entities adapted to perform the computing and networking functions, operations, and/or processes described herein without departing from the spirit and scope of embodiments of the present invention.


In certain illustrative embodiments, a system is provided for auditing the fill status of a customer waste container 20 by a waste services provider during performance of a waste service activity. Optical sensor 70 is disposed on waste collection vehicle 15 and configured to capture image data of customer container 20 that is indicative of the fill status of container 20. Central server 35 may utilize memory storage area 95, and processor 75 in communication with memory storage area 95 to, in real time during performance of the waste service activity, receive the image data from optical sensor 70, compare the fill status from the image data to a predetermined overload threshold condition (or “POTC”) for customer container 20 stored in memory storage area 95, and determine, based on the comparison, whether the fill status has met or exceeded the predetermined overload threshold condition. If the fill status has met or surpassed the predetermined overload threshold condition, an action proposal can be generated, from which one or more actions can be executed. The actions can comprise, for example, one or more of: (i) a customer communication, (ii) a customer billing adjustment, and (iii) a container recovery instruction for customer container 20 for delivery to waste collection vehicle 15.


The presently disclosed waste management system can allow a waste service provider to audit the status of a customer waste container 20 during performance of a waste service activity. In certain illustrative embodiments, the system and method disclosed herein can also be utilized to perform “audits” in industries other than the waste industry, where auditing of containers using optical sensors and associated computer functionality are utilized.


In certain illustrative embodiments, software 90 can execute the flow of the method steps of FIGS. 5-8 interacting with the various system elements of FIGS. 1-4. In the illustrative embodiment shown in FIG. 5, the method can be initiated when an image or video of a customer container is received from an optical sensor on a waste service vehicle (Step 501). The location of the waste service vehicle can then be identified (Step 502), and can be associated with a customer identity in the database based on stored customer information such as address (Step 503). Once the customer identity is established, a determination can be made of whether the fill status of the customer waste container in the image or video meets or exceeds the predetermined overload threshold condition (“POTC”) for that particular customer (Step 504). If the answer is yes, an action proposal for the customer can be generated (Step 505). If desired, user input can be utilized to analyze the action proposal, and amend as necessary. For example, the user can pick one or more of these options from the action proposal for execution. One or more actions can then be executed from the action proposal (Step 506).


In the illustrative embodiment shown in FIG. 6, the method can be initiated when the location of the waste service vehicle is identified (Step 601). The location of the waste service vehicle can then be associated with a customer identity in the database based on stored customer information such as address (Step 602). An image or video of a customer container can be received from an optical sensor on a waste service vehicle (Step 603), and a determination can be made of whether the fill status of the customer waste container in the image or video meets or exceeds the predetermined overload threshold condition (“POTC”) for that particular customer (Step 604). If the answer is yes, an action proposal for the customer can be generated (Step 605). If desired, user input can be utilized to analyze the action proposal, and amend as necessary. For example, the user can pick one or more of these options from the action proposal for execution. One or more actions can then be executed from the action proposal (Step 606).


The illustrative embodiment shown in FIG. 6 differs from that shown in FIG. 5 in that the identification of the location of the vehicle and the identity of the associated customer is performed before, instead of after, the image is received from the waste service vehicle.


In the illustrative embodiment shown in FIG. 7, the method can be initiated when an image or video of a customer container is received from an optical sensor on a waste service vehicle (Step 701). The customer can then be identified (Step 702), and associated with stored customer information in the database (Step 703). Next, a determination can be made of whether the fill status of the customer waste container in the image or video meets or exceeds the predetermined overload threshold condition (“POTC”) for that particular customer (Step 704). If the answer is yes, an action proposal for the customer can be generated (Step 705). User input can be utilized to analyze the action proposal, and amend as necessary. For example, the user can pick one or more of these options from the action proposal for execution. One or more actions can then be executed from the action proposal (Step 706). The illustrative embodiment shown in FIG. 7 differs from that shown in FIG. 6 in that no location identifying is utilized to identify the customer. For example, the customer identify may already be known, or obtainable, via other means.


In the illustrative embodiment shown in FIG. 8, the method can be initiated when the customer is identified (Step 801), and associated with stored customer information in the database. Next, an image or video of a customer container is received from an optical sensor on a waste service vehicle (Step 802). A determination can be made of whether the fill status of the customer waste container in the image or video meets or exceeds the predetermined overload threshold condition (“POTC”) for that particular customer (Step 803). If the answer is yes, an action proposal for the customer can be generated (Step 804). User input can be utilized to analyze the action proposal, and amend as necessary. For example, the user can pick one or more of these options from the action proposal for execution. One or more actions can then be executed from the action proposal (Step 805). The illustrative embodiment shown in FIG. 8 differs from that shown in FIG. 7 in that the identity of the associated customer is performed before, instead of after, the image is received from the waste service vehicle.


In certain illustrative embodiments, and as illustrated in FIG. 9, the image(s) captured and stored by optical sensor 70 and communicated to central server 35 may be compared (e.g., by processor 75) with the pictures and/or descriptions stored in memory storage area 95 to determine if any objects in the image(s) match any particular picture and/or description, and thus meet or exceed predetermined overload threshold condition (“POTC”). FIG. 9 represents an overall depiction of how the determination could occur, in certain illustrative embodiments. In some cases, the images can be displayed on a video screen with graphical user interface for viewing and interaction by a user, such that the user can participate in making the determination.


In certain illustrative embodiments, the POTC can be customer specific. Alternatively, the POTC does not need to be associated with any particular customer, and can instead be a standard condition established by the waste service provider based on any number of conditions and requirements. If desired, a user of the system can double check or confirm the determination of “overloaded” status made by the processor by soliciting a visual confirmation from the driver onsite.


In certain illustrative embodiments, processor 75 may automatically review the accumulated images and determine whether predetermined overload threshold condition (“POTC”) is met or exceeded based on machine learning and in association with programmed recognition patterns. In particular, processor 75 may be taught to recognize, for example, patterns of shapes, or sizes, that indicate trash protruding from the top or sides of container 20, based on existing images in the database. Object recognition software may also be used for this purpose. In the flowchart of FIG. 5, for example, if no objects within the image match the picture and/or description of the sought-after items when Step 504 is performed, control may return to Step 501. However, when one or more objects recognized in the image captured by optical sensor 70 substantially match (e.g., within a threshold margin) the picture and/or description received at Step 501, then an action proposal will be generated at Step 505.


In certain illustrative embodiments, the comparing and determining are performed using machine learning based on a set of programmed data associated with the predetermined overload threshold condition for the exemplary customer waste container. The set of programmed data can include a plurality of images of the exemplary customer waste container. Each image of the exemplary customer waste container can display a different exemplary fill status condition, where a first subsection of the plurality of images is pre-identified, based on the exemplary fill status condition, as meeting or exceeding the predetermined overload threshold condition, and where a second subsection of the plurality of images is pre-identified, based on the exemplary fill status condition, as not meeting or exceeding the predetermined overload threshold condition. The pre-identification of an image in the set of programmed data as meeting or exceeding, or not meeting or exceeding, the predetermined overload threshold condition can be based upon one or more features in the image such as an open or closed status of the lid of the exemplary customer waste container, a presence or absence of waste on the ground adjacent the exemplary customer waste container, or an identification of excess waste in a defined region above the rim of the exemplary customer waste container when the lid of the exemplary customer waste container is at least partially open. The processor can be trained, using machine learning or via programming, to recognize and identify the fill status of the customer waste container based on the image data received from the optical sensor. The recognition and identifying of the fill status of the customer waste container can also be based upon one or more features in the image data such an open or closed status of the lid of the customer waste container, a presence or absence of waste on the ground adjacent the customer waste container, and an identification of excess waste in a defined region above the rim of the customer waste container when the lid of the customer waste container is at least partially open. The processor can be trained, using machine learning, to match the recognized fill status of the customer waste container with the image of the exemplary customer waste container in the set of programmed data that has a corresponding fill status, and then to categorize the fill status of the customer waste container as either (i) meeting or exceeding, or (ii) not meeting or exceeding, the predetermined overload threshold condition.


In certain illustrative embodiments, one or more action proposals can be generated based on the identifications above. The actions proposals can include, for example, recommendations to (i) remove excess waste from customer container, (ii) remove and replace container, (iii) provide additional containers, (iv) provide reporting, education and/or instructions to customer, or (v) to adjust customer billing. In addition, historical account information and attributes of target customer and “like” customers can be collected, and the action proposals for target customers can be determined and ranked based on lifetime value impact scoring. Additional information can also be collected from the Internet or other outside sources. Scoring of target customer can be impacted based on prior proposals or interactions as well as preferences/acceptances of “like” customers to similar action proposals, and restrictions or constraints from target customer's attributes can be applied. Action proposals can be delivered to appropriate user/system for acceptance, and thereupon, the action proposal can be executed/applied, which can include charging the customer for the overage, notifying the customer of the overage through a proactive warning and notification process (including still images and/or video), and noting the overage incident on the customer's account.


In certain illustrative embodiments, a method is provided for collecting, processing, and applying data from a waste service vehicle to increase customer lifetime value through targeted action proposals. The method can include the steps of: collecting information (such as image, video, collection vehicle, driver inputs) at a target service location; matching customer account to a target service location; processing information from the target service location and historical customer account record to create an action proposal; and executing an action from the action proposal. The information that can be processed can include a variety of gathered information, for example, information regarding safety, receptacle condition, receptacle contents, fill status, site conditions, obstructions (temporary or permanent), service, service quality (verification, receptacle identification, receptacle contents), service audit (size, frequency, location, and quantity), service exceptions (unable to service, site obstructions), site damage, theft/poaching/no customer, sustainability, material diversion/audits, dangerous/hazardous materials, savings, site service times, bin locations and ancillary services (locks, gates, etc).


The presently disclosed subject matter has a variety of practical applications, as well as provides solutions to a number of technological and business problems of the prior art. For example, accuracy in customer billing is improved. A critical component of providing waste services to residential and commercial customers is accuracy in the customer's statement. The presently disclosed system and method allows the waste services provider to determine if the waste container or bin is overloaded resulting in the customer requiring additional service beyond the capacity of the container or bin. Improved management and education of customers regarding service requirements also occurs. An obligation of the waste service provider is to manage and educate the residential and commercial customer of the waste collection company's service requirements. The system and method of recording and auditing service related and non-service related activities outside of the waste collection vehicle allows the end-user to educate the customer on closing the container or bin lid to reduce capturing of precipitation, to reduce litter/blight, to reduce unauthorized dumping or use, and to reduce animals and vermin from intruding the container or bin, as well as the dangers and hardships associated with overloading a container or bin.


Improvements in employee and public safety also occur. An obligation of the waste service provider is to provide a safe working environment for its employees and its customers. The presently disclosed system and method allows the end-user to: (i) improve safety and protects its employees and equipment by reducing overloaded containers, which damage equipment, cause collection vehicle fires, cause other property damage from falling debris and otherwise puts its employees at risk; (ii) improve safety by identifying and abating dangerous stops and hard to service accounts, which result in vehicle accidents and employee injuries; (iii) improve safety and reduce vehicle accidents by having safe access to containers and bins; and (v) improve safety by identifying and correcting overloaded containers and bins at customer's service location.


Improved customer service can also be provided. The cornerstone of a successful waste collection provider is providing excellent customer service. The system and method disclosed herein allows the end-user to: (i) proactively notify the customer of waste collection service requirements to ensure safe and efficient waste collection; (ii) demonstrate a container is overloaded or unavailable for service and assist the customer in efforts to receive timely service; (iii) educate the customer on proper recycling and management of waste in each of the containers or bins; and (iv) proactively remove or repair damaged and/or leaking containers and bins.


Operational Improvements can also occur. Operational improvements result in more efficient waste collection services and ultimately improved earnings, safety and employee morale. The system and method disclosed herein allow the end-user to: (i) reduce overloaded containers resulting in less equipment damage, employee injuries and time off-route; (ii) improved route efficiencies by servicing readily accessible containers and bins; and (iii) supporting frontline employees by holding customer to waste collector's service requirements.


Those skilled in the art will appreciate that certain portions of the subject matter disclosed herein may be embodied as a method, data processing system, or computer program product. Accordingly, these portions of the subject matter disclosed herein may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, portions of the subject matter disclosed herein may be a computer program product on a computer-usable storage medium having computer readable program code on the medium. Any suitable computer readable medium may be utilized including hard disks, CD-ROMs, optical storage devices, or other storage devices. Further, the subject matter described herein may be embodied as systems, methods, devices, or components. Accordingly, embodiments may, for example, take the form of hardware, software or any combination thereof, and/or may exist as part of an overall system architecture within which the software will exist. The present detailed description is, therefore, not intended to be taken in a limiting sense.


It is to be understood that the present invention is not limited to the embodiment(s) described above and illustrated herein, but encompasses any and all variations falling within the scope of the appended claims.

Claims
  • 1. A method for auditing the fill status of a customer waste container by a waste service provider during performance of a waste service activity, the method comprising: capturing image data of the customer waste container that is indicative of the fill status of the container, wherein the image data is captured using an optical sensor located on a waste collection vehicle, and wherein the customer waste container is located at a customer site and wherein the direction of image capture of the optical sensor is outward facing with respect to the waste collection vehicle and towards the customer waste container at the customer site;comparing the fill status from the image data to a predetermined overload threshold condition for the customer waste container;determining, based on the comparison, whether the fill status has met or exceeded the predetermined overload threshold condition, wherein the determination is made using machine learning to recognize and identify the fill status of the customer waste container based on the image data received from the optical sensor, and wherein the predetermined overload threshold condition is associated with existing images stored in the memory storage area;if the fill status has met or surpassed the predetermined overload threshold condition, generating an action proposal; andexecuting an action from the action proposal,wherein the processor is configured to identify the location of the waste collection vehicle and associate the location of the waste collection vehicle with the identity of the specific customer at that location,and wherein the comparing and determining are performed using machine learning based on a set of programmed data associated with the predetermined overload threshold condition for the exemplary customer waste container,and wherein the set of programmed data comprises a plurality of images of the exemplary customer waste container, and wherein each image of the exemplary customer waste container displays a different exemplary fill status condition,and wherein a first subsection of the plurality of images is pre-identified, based on the exemplary fill status condition, as meeting or exceeding the predetermined overload threshold condition, and wherein a second subsection of the plurality of images is pre-identified, based on the exemplary fill status condition, as not meeting or exceeding the predetermined overload threshold condition,and wherein the pre-identification of an image in the set of programmed data as meeting or exceeding, or not meeting or exceeding, the predetermined overload threshold condition is based upon at least one feature in the image comprising an open or closed status of the lid of the exemplary customer waste container, a presence or absence of waste on the ground adjacent the exemplary customer waste container, and an identification of excess waste in a defined region above the rim of the exemplary customer waste container when the lid of the exemplary customer waste container is at least partially open,and wherein the recognition and identifying of the fill status of the customer waste container can also be based upon one or more features in the image data comprising an open or closed status of the lid of the customer waste container, a presence or absence of waste on the ground adjacent the customer waste container, and an identification of excess waste in a defined region above the rim of the customer waste container when the lid of the customer waste container is at least partially open,and wherein the processor is trained, using machine learning, to match the recognized fill status of the customer waste container with the image of the exemplary customer waste container in the set of programmed data that has a corresponding fill status, and then categorize the fill status of the customer waste container as either meeting or exceeding, or not meeting or exceeding, the predetermined overload threshold condition,and wherein the pre-identification of an image in the set of programmed data as meeting or exceeding, or not meeting or exceeding, the predetermined overload threshold condition is based upon more than one of an open or closed status of the lid of the exemplary customer waste container, a presence or absence of waste on the ground adjacent the exemplary customer waste container, and an identification of excess waste in a defined region above the rim of the exemplary customer waste container when the lid of the exemplary customer waste container is at least partially open, and wherein the recognition and identifying of the fill status of the customer waste container is based upon more than one of the image data comprising an open or closed status of the lid of the customer waste container, a presence or absence of waste on the ground adjacent the customer waste container, and an identification of excess waste in a defined region above the rim of the customer waste container when the lid of the customer waste container is at least partially open.
  • 2. The method of claim 1, wherein the action comprises a container recovery instruction for the customer waste container for delivery to the waste collection vehicle to collect the customer waste container and remove the customer waste container from the customer location.
  • 3. The method of claim 1, wherein the action comprises a customer billing adjustment.
  • 4. The method of claim 1, wherein generating an action proposal comprises: collecting historical account information and attributes of the customer; collecting historical account information and attributes of similar customers of the waste services provider; developing a plurality of action proposals using the collected information; and scoring and ranking the action proposals to determine an action.
  • 5. The method of claim 1, wherein the action comprises a customer communication that comprises an educational message to the customer regarding container overages.
  • 6. The method of claim 1, wherein the predetermined overload threshold condition is specific to the customer at the customer site.
  • 7. The method of claim 1, further comprising soliciting a confirmation from a driver of the waste collection vehicle via visual inspection that the fill status has met or surpassed the predetermined overload threshold condition.
  • 8. The system of claim 1, wherein the action comprises a container recovery instruction for delivery to the waste collection vehicle to remove the customer waste container from the customer location and replace the customer waste container.
  • 9. The system of claim 1, wherein the action comprises a container recovery instruction for delivery to the waste collection vehicle to provide an additional container at the customer location.
  • 10. The system of claim 4, wherein the customer scoring is impacted by acceptances of similar action proposals by other customers of the waste services provider.
  • 11. The system of claim 1, wherein the predetermined overload threshold condition is specific to the particular customer receiving the customer communication.
  • 12. A system for auditing the fill status of a customer waste container by a waste services provider during performance of a waste service activity, the system comprising: an optical sensor disposed on a waste collection vehicle and configured to capture image data of the customer waste container that is indicative of the fill status of the container, wherein the customer waste container is located at a customer site and the direction of image capture for the optical sensor is outward facing with respect to the waste collection vehicle and towards the customer waste container at the customer site;a memory storage area, anda processor in communication with the memory storage area and configured to, in real time during performance of the waste service activity:receive the image data from the optical sensor;compare the fill status from the image data of the customer waste container to a predetermined overload threshold condition for an exemplary customer waste container stored in the memory storage area;determine, based on the comparison, whether the fill status of the customer waste container has met or exceeded the predetermined overload threshold condition;if the fill status has met or surpassed the predetermined overload threshold condition, generate an action proposal; andexecute an action from the action proposal,wherein the processor is trained, using machine learning, to recognize and identify the fill status of the customer waste container based on the image data received from the optical sensor, and wherein the predetermined overload threshold condition is associated with existing images stored in the memory storage area,wherein the processor is configured to identify the location of the waste collection vehicle and associate the location of the waste collection vehicle with the identity of the specific customer at that location,and wherein the comparing and determining are performed using machine learning based on a set of programmed data associated with the predetermined overload threshold condition for the exemplary customer waste container,and wherein the set of programmed data comprises a plurality of images of the exemplary customer waste container, and wherein each image of the exemplary customer waste container displays a different exemplary fill status condition,and wherein a first subsection of the plurality of images is pre-identified, based on the exemplary fill status condition, as meeting or exceeding the predetermined overload threshold condition, and wherein a second subsection of the plurality of images is pre-identified, based on the exemplary fill status condition, as not meeting or exceeding the predetermined overload threshold condition,and wherein the pre-identification of an image in the set of programmed data as meeting or exceeding, or not meeting or exceeding, the predetermined overload threshold condition is based upon at least one feature in the image comprising an open or closed status of the lid of the exemplary customer waste container, a presence or absence of waste on the ground adjacent the exemplary customer waste container, and an identification of excess waste in a defined region above the rim of the exemplary customer waste container when the lid of the exemplary customer waste container is at least partially open,and wherein the recognition and identifying of the fill status of the customer waste container can also be based upon one or more features in the image data comprising an open or closed status of the lid of the customer waste container, a presence or absence of waste on the ground adjacent the customer waste container, and an identification of excess waste in a defined region above the rim of the customer waste container when the lid of the customer waste container is at least partially open,and wherein the processor is trained, using machine learning, to match the recognized fill status of the customer waste container with the image of the exemplary customer waste container in the set of programmed data that has a corresponding fill status, and then categorize the fill status of the customer waste container as either meeting or exceeding, or not meeting or exceeding, the predetermined overload threshold condition,and wherein the pre-identification of an image in the set of programmed data as meeting or exceeding, or not meeting or exceeding, the predetermined overload threshold condition is based upon more than one of an open or closed status of the lid of the exemplary customer waste container, a presence or absence of waste on the ground adjacent the exemplary customer waste container, and an identification of excess waste in a defined region above the rim of the exemplary customer waste container when the lid of the exemplary customer waste container is at least partially open, and wherein the recognition and identifying of the fill status of the customer waste container is based upon more than one of the image data comprising an open or closed status of the lid of the customer waste container, a presence or absence of waste on the ground adjacent the customer waste container, and an identification of excess waste in a defined region above the rim of the customer waste container when the lid of the customer waste container is at least partially open.
  • 13. The system of claim 12, wherein the steps of identifying and associating are performed prior to receiving the image data from the optical sensor.
  • 14. The system of claim 12, wherein the steps of identifying and associating are performed subsequent to receiving the image data from the optical sensor.
  • 15. The system of claim 12, wherein the action comprises a container recovery instruction for the customer waste container for delivery to the waste collection vehicle to collect the customer waste container and remove the customer waste container from the customer location.
  • 16. The system of claim 12, wherein the action comprises a customer billing adjustment.
  • 17. The system of claim 12, wherein generating an action proposal comprises: collecting historical account information and attributes of the customer; collecting historical account information and attributes of similar customers of the waste services provider; developing a plurality of action proposals using the collected information; and scoring and ranking the action proposals to determine an action.
  • 18. The system of claim 12, wherein the action comprises a customer communication that comprises an educational message to the customer regarding container overages.
  • 19. The system of claim 12, wherein the action comprises a container recovery instruction for delivery to the waste collection vehicle to remove the customer waste container from the customer location and replace the customer waste container.
  • 20. The system of claim 12, wherein the action comprises a container recovery instruction for delivery to the waste collection vehicle to provide an additional container at the customer location.
  • 21. The system of claim 17, wherein the customer scoring is impacted by acceptances of similar action proposals by other customers of the waste services provider.
  • 22. The system of claim 12, wherein the predetermined overload threshold condition is specific to the particular customer receiving the customer communication.
  • 23. The system of claim 12, wherein the action proposal comprises charging the customer for the overage.
  • 24. The method of claim 12, wherein the action proposal comprises charging the customer for the overage.
RELATED APPLICATIONS

This Applications is a continuation application and claims the benefit, and priority benefit, of U.S. patent application Ser. No. 16/549,531, filed Aug. 23, 2019, the disclosure and contents of which are incorporated by reference herein in its entirety.

US Referenced Citations (311)
Number Name Date Kind
3202305 Herpich Aug 1965 A
5072833 Hansen Dec 1991 A
5230393 Mezey Jul 1993 A
5245137 Bowman et al. Sep 1993 A
5278914 Kinoshita et al. Jan 1994 A
5489898 Shigekusa et al. Feb 1996 A
5762461 Frohlingsdorf Jun 1998 A
5837945 Cornwell et al. Nov 1998 A
6097995 Tipton et al. Aug 2000 A
6408261 Durbin Jun 2002 B1
6448898 Kasik Sep 2002 B1
6510376 Burnstein et al. Jan 2003 B2
6563433 Fujiwara May 2003 B2
6729540 Ogawa May 2004 B2
6811030 Compton et al. Nov 2004 B1
7146294 Waitkus, Jr. Dec 2006 B1
7330128 Lombardo et al. Feb 2008 B1
7383195 Mallett et al. Jun 2008 B2
7406402 Waitkus, Jr. Jul 2008 B1
7501951 Maruca et al. Mar 2009 B2
7511611 Sabino et al. Mar 2009 B2
7536457 Miller May 2009 B2
7659827 Gunderson et al. Feb 2010 B2
7804426 Etcheson Sep 2010 B2
7817021 Date et al. Oct 2010 B2
7870042 Maruca et al. Jan 2011 B2
7878392 Mayers et al. Feb 2011 B2
7957937 Waitkus, Jr. Jun 2011 B2
7994909 Maruca et al. Aug 2011 B2
7999688 Healey et al. Aug 2011 B2
8020767 Reeves et al. Sep 2011 B2
8056817 Flood Nov 2011 B2
8146798 Flood et al. Apr 2012 B2
8185277 Flood et al. May 2012 B2
8269617 Cook et al. Sep 2012 B2
8314708 Gunderson et al. Nov 2012 B2
8330059 Curotto Dec 2012 B2
8332247 Bailey et al. Dec 2012 B1
8373567 Denson Feb 2013 B2
8374746 Plante Feb 2013 B2
8384540 Reyes et al. Feb 2013 B2
8485301 Grubaugh et al. Jul 2013 B2
8508353 Cook et al. Aug 2013 B2
8542121 Maruca et al. Sep 2013 B2
8550252 Borowski et al. Oct 2013 B2
8564426 Cook et al. Oct 2013 B2
8564446 Gunderson et al. Oct 2013 B2
8602298 Gonen Dec 2013 B2
8606492 Botnen Dec 2013 B1
8630773 Lee et al. Jan 2014 B2
8645189 Lyle Feb 2014 B2
8674243 Curotto Mar 2014 B2
8676428 Richardson et al. Mar 2014 B2
8714440 Flood et al. May 2014 B2
8738423 Lyle May 2014 B2
8744642 Nemat-Nasser et al. Jun 2014 B2
8803695 Denson Aug 2014 B2
8818908 Altice et al. Aug 2014 B2
8849501 Cook et al. Sep 2014 B2
8854199 Cook et al. Oct 2014 B2
8862495 Ritter Oct 2014 B2
8880279 Plante Nov 2014 B2
8930072 Lambert et al. Jan 2015 B1
8952819 Nemat-Nasser Feb 2015 B2
8970703 Thomas, II et al. Mar 2015 B1
8996234 Tamari et al. Mar 2015 B1
9047721 Botnen Jun 2015 B1
9058706 Cheng Jun 2015 B2
9098884 Borowski et al. Aug 2015 B2
9098956 Lambert et al. Aug 2015 B2
9111453 Alselimi Aug 2015 B1
9158962 Nemat-Nasser et al. Oct 2015 B1
9180887 Nemat-Nasser et al. Nov 2015 B2
9189899 Cook et al. Nov 2015 B2
9226004 Plante Dec 2015 B1
9235750 Sutton et al. Jan 2016 B1
9238467 Hoye et al. Jan 2016 B1
9240079 Lambert et al. Jan 2016 B2
9240080 Lambert et al. Jan 2016 B2
9245391 Cook et al. Jan 2016 B2
9247040 Sutton Jan 2016 B1
9251388 Flood Feb 2016 B2
9268741 Lambert et al. Feb 2016 B1
9275090 Denson Mar 2016 B2
9280857 Lambert et al. Mar 2016 B2
9292980 Cook et al. Mar 2016 B2
9298575 Tamari et al. Mar 2016 B2
9317980 Cook et al. Apr 2016 B2
9330287 Graczyk et al. May 2016 B2
9341487 Bonhomme May 2016 B2
9342884 Mask May 2016 B2
9344683 Nemat-Nasser et al. May 2016 B1
9347818 Curotto May 2016 B2
9358926 Lambert et al. Jun 2016 B2
9373257 Bonhomme Jun 2016 B2
9389147 Lambert et al. Jul 2016 B1
9390568 Nemat-Nasser et al. Jul 2016 B2
9396453 Hynes et al. Jul 2016 B2
9401985 Sutton Jul 2016 B2
9403278 Van Kampen et al. Aug 2016 B1
9405992 Badholm et al. Aug 2016 B2
9418488 Lambert Aug 2016 B1
9428195 Surpi Aug 2016 B1
9442194 Kurihara et al. Sep 2016 B2
9463110 Nishtala et al. Oct 2016 B2
9466212 Stumphauzer, II et al. Oct 2016 B1
9472083 Nemat-Nasser Oct 2016 B2
9495811 Herron Nov 2016 B2
9501690 Nemat-Nasser et al. Nov 2016 B2
9520046 Call et al. Dec 2016 B2
9525967 Mamlyuk Dec 2016 B2
9546040 Flood et al. Jan 2017 B2
9573601 Hoye et al. Feb 2017 B2
9574892 Rodoni Feb 2017 B2
9586756 O'Riordan et al. Mar 2017 B2
9589393 Botnen Mar 2017 B2
9594725 Cook et al. Mar 2017 B1
9595191 Surpi Mar 2017 B1
9597997 Mitsuta et al. Mar 2017 B2
9604648 Tamari et al. Mar 2017 B2
9633318 Plante Apr 2017 B2
9633576 Reed Apr 2017 B2
9639535 Ripley May 2017 B1
9646651 Richardson May 2017 B1
9650051 Hoye et al. May 2017 B2
9679210 Sutton et al. Jun 2017 B2
9685098 Kypri Jun 2017 B1
9688282 Cook et al. Jun 2017 B2
9702113 Kotaki et al. Jul 2017 B2
9707595 Ripley Jul 2017 B2
9721342 Mask Aug 2017 B2
9734717 Surpi et al. Aug 2017 B1
9754382 Rodoni Sep 2017 B1
9766086 Rodoni Sep 2017 B1
9778058 Rodoni Oct 2017 B2
9803994 Rodoni Oct 2017 B1
9824336 Borges et al. Nov 2017 B2
9824337 Rodoni Nov 2017 B1
9834375 Jenkins et al. Dec 2017 B2
9852405 Rodoni et al. Dec 2017 B1
10029685 Hubbard et al. Jul 2018 B1
10152737 Lyman Dec 2018 B2
10198718 Rodoni Feb 2019 B2
10210623 Rodoni Feb 2019 B2
10255577 Steves et al. Apr 2019 B1
10311501 Rodoni Jun 2019 B1
10332197 Kekalainen et al. Jun 2019 B2
10354232 Tomlin, Jr. et al. Jul 2019 B2
10382915 Rodoni Aug 2019 B2
10410183 Bostick et al. Sep 2019 B2
10594991 Skolnick Mar 2020 B1
10750134 Skolnick Aug 2020 B1
10855958 Skolnick Dec 2020 B1
10911726 Skolnick Feb 2021 B1
11074557 Flood Jul 2021 B2
11128841 Skolnick Sep 2021 B1
11140367 Skolnick Oct 2021 B1
11172171 Skolnick Nov 2021 B1
11222491 Romano et al. Jan 2022 B2
11373536 Savchenko Jun 2022 B1
11386362 Kim Jul 2022 B1
11425340 Skolnick Aug 2022 B1
20020069097 Conrath Jun 2002 A1
20020077875 Nadir Jun 2002 A1
20020125315 Ogawa Sep 2002 A1
20020194144 Berry Dec 2002 A1
20030014334 Tsukamoto Jan 2003 A1
20030031543 Elbrink Feb 2003 A1
20030069745 Zenko Apr 2003 A1
20030191658 Rajewski Oct 2003 A1
20030233261 Kawahara et al. Dec 2003 A1
20040039595 Berry Feb 2004 A1
20040167799 Berry Aug 2004 A1
20050038572 Krupowicz Feb 2005 A1
20050080520 Kline et al. Apr 2005 A1
20050182643 Shirvanian Aug 2005 A1
20050209825 Ogawa Sep 2005 A1
20050261917 Forget Shield Nov 2005 A1
20060235808 Berry Oct 2006 A1
20070150138 Plante Jun 2007 A1
20070260466 Casella et al. Nov 2007 A1
20070278140 Mallett et al. Dec 2007 A1
20080010197 Scherer Jan 2008 A1
20080077541 Scherer et al. Mar 2008 A1
20080202357 Flood Aug 2008 A1
20080234889 Sorensen Sep 2008 A1
20090014363 Gonen et al. Jan 2009 A1
20090024479 Gonen et al. Jan 2009 A1
20090055239 Waitkus, Jr. Feb 2009 A1
20090083090 Rolfes et al. Mar 2009 A1
20090126473 Porat et al. May 2009 A1
20090138358 Gonen et al. May 2009 A1
20090157255 Plante Jun 2009 A1
20090161907 Healey Jun 2009 A1
20100017276 Wolff et al. Jan 2010 A1
20100071572 Carroll et al. Mar 2010 A1
20100119341 Flood et al. May 2010 A1
20100175556 Kummer Jul 2010 A1
20100185506 Wolff et al. Jul 2010 A1
20100217715 Lipcon Aug 2010 A1
20100312601 Lin Dec 2010 A1
20110108620 Wadden et al. May 2011 A1
20110137776 Goad Jun 2011 A1
20110208429 Zheng et al. Aug 2011 A1
20110225098 Wolff et al. Sep 2011 A1
20110260878 Rigling Oct 2011 A1
20110279245 Hynes et al. Nov 2011 A1
20110316689 Reyes Dec 2011 A1
20120029980 Paz et al. Feb 2012 A1
20120029985 Wilson et al. Feb 2012 A1
20120047080 Rodatos Feb 2012 A1
20120262568 Ruthenberg Oct 2012 A1
20120265589 Whittier Oct 2012 A1
20120310691 Carlsson et al. Dec 2012 A1
20130024335 Lok Jan 2013 A1
20130039728 Price et al. Feb 2013 A1
20130041832 Rodatos Feb 2013 A1
20130075468 Wadden et al. Mar 2013 A1
20130332238 Lyle Dec 2013 A1
20130332247 Gu Dec 2013 A1
20140060939 Eppert Mar 2014 A1
20140112673 Sayama Apr 2014 A1
20140114868 Wan et al. Apr 2014 A1
20140172174 Poss et al. Jun 2014 A1
20140214697 Mcsweeney Jul 2014 A1
20140236446 Spence Aug 2014 A1
20140278630 Gates et al. Sep 2014 A1
20140379588 Gates Dec 2014 A1
20150095103 Rajamani et al. Apr 2015 A1
20150100428 Parkinson, Jr. Apr 2015 A1
20150144012 Frybarger May 2015 A1
20150278759 Harris et al. Oct 2015 A1
20150294431 Fiorucci et al. Oct 2015 A1
20150298903 Luxford Oct 2015 A1
20150302364 Calzada et al. Oct 2015 A1
20150307273 Lyman Oct 2015 A1
20150324760 Borowski et al. Nov 2015 A1
20150326829 Kurihara et al. Nov 2015 A1
20150348252 Mask Dec 2015 A1
20150350610 Loh Dec 2015 A1
20160021287 Loh Jan 2016 A1
20160044285 Gasca et al. Feb 2016 A1
20160179065 Shahabdeen Jun 2016 A1
20160187188 Curotto Jun 2016 A1
20160224846 Cardno Aug 2016 A1
20160232498 Tomlin, Jr. et al. Aug 2016 A1
20160239689 Flood Aug 2016 A1
20160247058 Kreiner et al. Aug 2016 A1
20160292653 Gonen Oct 2016 A1
20160300297 Kekalainen et al. Oct 2016 A1
20160321619 Inan et al. Nov 2016 A1
20160334236 Mason et al. Nov 2016 A1
20160335814 Tamari et al. Nov 2016 A1
20160372225 Lefkowitz et al. Dec 2016 A1
20160377445 Rodoni Dec 2016 A1
20160379152 Rodoni Dec 2016 A1
20160379154 Rodoni Dec 2016 A1
20170008671 Whitman et al. Jan 2017 A1
20170011363 Whitman et al. Jan 2017 A1
20170029209 Smith et al. Feb 2017 A1
20170046528 Lambert Feb 2017 A1
20170061222 Hoye et al. Mar 2017 A1
20170076249 Byron et al. Mar 2017 A1
20170081120 Liu et al. Mar 2017 A1
20170086230 Azevedo et al. Mar 2017 A1
20170109704 Lettieri et al. Apr 2017 A1
20170116583 Rodoni Apr 2017 A1
20170116668 Rodoni Apr 2017 A1
20170118609 Rodoni Apr 2017 A1
20170121107 Flood et al. May 2017 A1
20170124533 Rodoni May 2017 A1
20170154287 Kalinowski et al. Jun 2017 A1
20170176986 High et al. Jun 2017 A1
20170193798 Call et al. Jul 2017 A1
20170200333 Plante Jul 2017 A1
20170203706 Reed Jul 2017 A1
20170221017 Gonen Aug 2017 A1
20170243269 Rodini et al. Aug 2017 A1
20170243363 Rodoni Aug 2017 A1
20170277726 Huang et al. Sep 2017 A1
20170308871 Tallis Oct 2017 A1
20170330134 Botea Nov 2017 A1
20170344959 Bostick et al. Nov 2017 A1
20170345169 Rodoni Nov 2017 A1
20170350716 Rodoni Dec 2017 A1
20170355522 Salinas et al. Dec 2017 A1
20170364872 Rodoni Dec 2017 A1
20180012172 Rodoni Jan 2018 A1
20180025329 Podgorny et al. Jan 2018 A1
20180075417 Gordon Mar 2018 A1
20180158033 Woods et al. Jun 2018 A1
20180194305 Reed Jul 2018 A1
20180245940 Dong et al. Aug 2018 A1
20180247351 Rodoni Aug 2018 A1
20190005466 Rodoni Jan 2019 A1
20190019167 Candel et al. Jan 2019 A1
20190050879 Zhang et al. Feb 2019 A1
20190056416 Rodoni Feb 2019 A1
20190065901 Amato et al. Feb 2019 A1
20190196965 Zhang et al. Jun 2019 A1
20190197498 Gates et al. Jun 2019 A1
20190210798 Schultz Jul 2019 A1
20190217342 Parr et al. Jul 2019 A1
20190244267 Rattner et al. Aug 2019 A1
20190311333 Kekalainen Oct 2019 A1
20200082167 Shalom et al. Mar 2020 A1
20200109963 Zass Apr 2020 A1
20200175556 Podgorny Jun 2020 A1
20200191580 Christensen et al. Jun 2020 A1
20210188541 Kurani et al. Jun 2021 A1
20210217156 Balachandran et al. Jul 2021 A1
Foreign Referenced Citations (29)
Number Date Country
2632738 May 2016 CA
2632689 Oct 2016 CA
101482742 Jul 2009 CN
101512720 Aug 2009 CN
105787850 Jul 2016 CN
105929778 Sep 2016 CN
106296416 Jan 2017 CN
69305435 Apr 1997 DE
69902531 Apr 2003 DE
102012006536 Oct 2013 DE
577540 Oct 1996 EP
1084069 Aug 2002 EP
2028138 Feb 2009 EP
2447184 Sep 2008 GB
3662616 Jun 2005 JP
2012-206817 Oct 2012 JP
2013-142037 Jul 2013 JP
9954237 Oct 1999 WO
2007067772 Jun 2007 WO
2007067775 Jun 2007 WO
2012069839 May 2012 WO
2012172395 Dec 2012 WO
2016074608 May 2016 WO
2016187677 Dec 2016 WO
2017070228 Apr 2017 WO
2017179038 Oct 2017 WO
2018182858 Oct 2018 WO
2018206766 Nov 2018 WO
2018215682 Nov 2018 WO
Non-Patent Literature Citations (29)
Entry
US 9,092,921 B2, 07/2015, Lambert et al. (withdrawn)
Khan R, Kumar S, Srivastava AK, Dhingra N, Gupta M, Bhati N, Kumari P. Machine Learning and IoT-Based Waste Management Model. Comput Intell Neurosci. Aug. 26, 2021;2021:5942574. doi: 10.1155/2021/5942574. PMID: 34484322; PMCID: PMC8416408. (Year: 2021).
K. Mikami, Y. Chen, J. Nakazawa, Y. Iida, Y. Kishimoto and Y. Oya, “DeepCounter: Using Deep Learning to Count Garbage Bags,” 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), 2018, pp. 1-10, doi: 10.1109/RTCSA.2018.00010. (Year: 2018).
Nilopherjan, N. et al.; Automatic Garbage vol. Estimation Using SIFT Features Through Deep Neural Networks and Poisson Surface Reconstruction; International Journal of Pure and Applied Mathematics; vol. 119, No. 14; 2015; pp. 1101-1107.
Ghongane, Aishwarya et al.; Automatic Garbage Tracking and Collection System; International Journal of Advanced Technology in Engineering and Science; vol. 5, No. 4; Apr. 2017; pp. 166-173.
Rajani et al.; Waste Management System Based on Location Intelligence; 4 pages; Poojya Doddappa Appa Colleage of Engineering, Kalaburgi.
Waste Management Review; A clear vison on waste collections; Dec. 8, 2015; 5 pages; http://wastemanagementreiew.com/au/a-clear-vison-on-waste-collections/.
Waste Management Surveillance Solutiosn; Vehicle Video Cameral; Aug. 23, 2017; 6 pages; http://vehiclevideocameras.com/mobile-video-applications/waste-management-camera.html.
Rich, John I.; Truck Equipment: Creating a Safer Waste Truck Environment; Sep. 2013; pp. 18-20; WasteAdvantage Magainze.
Town of Prosper; News Release: Solid Waste Collection Trucks Equipped wit “Third Eye,” video system aborad trash and recycling trucks to improve service; Jan. 13, 2017; 1 page; U.S.
Product News Network; Telematics/Live Video System Increases Driver Safety/Productivity; Mar. 30, 2015; 3 pages; Thomas Industrial Network, Inc.
Karidis, Arlene; Waste Pro to Install Hight-Tech Camera Systems in all Trucks to Address Driver Safety; Mar. 10, 2016; 2 pages; Wastedive.com.
Greenwalt, Megan; Finnish Company Uses IoT to Digitize Trash Bins; Sep. 14, 2016; 21 pages; www.waste360.com.
Georgakopoulos, Chris; Cameras Cut Recycling Contamination; The Daily Telegraph; Apr. 7, 2014; 2 pages.
Van Dongen, Matthew; Garbage ‘Gotcha’ Videos on Rise in City: Residents Irked Over Perceived Infractions Nov. 18, 2015; 3 pages; The Spectator.
The Advertiser; Waste Service Drives Innovation; Jan. 25, 2016; 2 pages; Fairfax Media Publications Pty Limited; Australia.
rwp-wasteportal.com; Waste & Recycling Data Portal and Software; 16 pages; printed Oct. 3, 2019.
Bhargava, Hermant K. et al.; A Web-Based Decision Support System for Waste Disposal and Recycling; pp. 47-65; 1997; Comput.Environ. and Urban Systems, vol. 21, No. 1; Pergamon.
Kontokasta, Constantine E. et al.; Using Machine Learning and Small Area Estimation to Predict Building-Level Municipal Solid Waste Generation in Cities; pp. 151-162; 2018; Computer, Envieonment and Urban Systems Elsevier.
Ferrer, Javier et al.; BIN-CT: Urban Waste Collection Based on Predicting the Container Fill Level; Apr. 23, 2019; 11 pages; Elsevier.
Vu, Hoang Lan et al.; Waste Management: Assessment of Waste Characteristics and Their Impact on GIS Vechicle Collection Route Optimization Using ANN Waste Forecasts; Environmental Systems Engineering; Mar. 22, 2019; 13 pages; Elsevier.
Hina, Syeda Mahlaqa; Municipal Solid Waste Collection Route Optimization Using Geospatial Techniques: A Case Study of Two Metropolitan Cities of Pakistan; Feb. 2016; 205 pages; U.S.
Kannangara, Miyuru et al.; Waste Management: Modeling and Prediction of Regional Municipal Soid Waste Generation and Diversion in Canada Using Machine Learning Approaches; Nov. 30, 2017; 3 pages; Elsevier.
Tan, Kah Chun et al.; Smart Land: AI Waste Sorting System; University of Malaya; 2 pages; Keysight Techonogies.
Oliveira, Veronica et al.; Journal of Cleaner Production: Artificial Neural Network Modelling of the Amount of Separately-Collected Household Packaging Waste; Nov. 8, 2018; 9 pages; Elsevier.
Zade, Jalili Ghazi et al.; Prediction of Municipal Solid Waste Generation by Use of Artificial Neural Network: A Case Study of Mashhad; Winter 2008; 10 pages; Int. J. Environ. Res., 2(1).
Sein, Myint Myint et al.; Trip Planning Query Based on Partial Sequenced Route Algorithm; 2019 IEEE 8th Global Conference; pp. 778-779.
A.F., Thompson et al.; Application of Geographic Information System to Solid Waste Management; Pan African International Conference on Information Science, Computing and Telecommunications; 2013; pp. 206-211.
Malakahmad, Amirhossein et al.; Solid Waste Collection System in Ipoh City, A Review; 2011 International Conference on Business, Engineering and Industrial Applications; pp. 174-179.
Continuations (1)
Number Date Country
Parent 16549531 Aug 2019 US
Child 16738613 US