The field of the invention generally relates to systems for detecting, characterizing and presenting information regarding nearby wildlife, and in particular a system to facilitate birdwatching.
Birdwatching is considered to be one of the fastest growing outdoor activities worldwide. Traditionally, the common equipment used for this experience is the human natural auditory and visual system and a physical bird species reference manual or guide. The experience may be enhanced visually through binoculars once an auditory sound or visual cue is identified. Other equipment used are high-performance cameras where the user manually tracks the target of interest to capture unique observations. More recently, bird electronic reference manuals have been released via various interactive mediums. However, improvements in the field are desired.
Various embodiments are presented of a system and method for performing one or more of identifying, directionally finding, and tracking birds of interest while birdwatching. The system may also be used to create a real-time and/or non-real-time interactive birdwatching experience for the user.
In some embodiments, the birdwatching system may comprise an apparatus, such as shaft, which includes a plurality of microphones located on a distal end of the shaft. The microphone array may be configured to receive audio signals of a bird and produce resultant audio signals as well as directional information of the received audio signals. The shaft may be configured to be supported by a backpack carried by a user such that the distal end of the shaft protrudes out of the backpack, and preferably near or above the head of the user. The apparatus may further comprise one or more video cameras located at the distal end of the shaft and configured to capture video images of bird(s). The apparatus may further comprise one or more speakers located at the distal end of the shaft and configured to generate bird sounds for attracting desired species of birds.
The birdwatching system may further comprise a device which includes a display, a non-transitory memory medium, and a processor communicatively coupled to the plurality of microphones, the display and the non-transitory memory medium. The device may be configured to receive audio data from the plurality of microphones, wherein the audio data corresponds to the audio signals of the bird, and wherein the audio data includes the directional information. The device may be further configured to process the audio data to determine a first bird species and a first location of the bird. The display may be configured to display a map of an area surrounding the microphone, and may also display a first icon indicating the first location of the bird on the map. The display may further selectively display information regarding the first bird species. The first icon may be selectable to display information associated with the first bird species.
The device may be a user equipment (UE) device carried by the user while birdwatching. The birdwatching system may further comprise a wearable audio presentation device, such as headphones, communicatively coupled to the UE, which can play the audio data for the user.
In some embodiments, the device is configured to transmit the first audio data to a server using the radio. The server may be configured to process the audio data, using one or more stored bird sound waveforms, to determine a first bird species of the bird, and to further determine a first location associated with the audio data. The device may then receive information from the server indicating a first bird species and a first location associated with the first audio data, based on the transmitted first audio data. The device may then display: 1) a map of an area surrounding the microphone, 2) a first icon on the map indicating the first location of the first bird, and 3) information regarding the first bird species.
The birdwatching system may be useable to detect, locate, and display information on a plurality of birds simultaneously. Thus when audio signals of multiple birds are received concurrently, the device may process each of the audio signals and present different respective icons on the display indicating locations of each of the detected birds. Alternatively, the device may transmit the plurality of audio signals corresponding to the different birds to the server for processing, and may receive back species and location information for each of the birds for presentation to the user on the display.
Some embodiments may comprise a server for use in bird watching, wherein the server may comprise a processor and a non-transitory memory medium. The server may be configured to receive audio data of a bird over a wide area network from the device (UE) of a user (birdwatcher). The audio data may be generated from a plurality of microphones, wherein the audio data comprises audio signals corresponding to sounds of the bird and includes direction information indicating a direction of the bird relative to the plurality of microphones. The server may process the audio data, using one or more stored bird sound waveforms, to determine a first bird species of the bird, and to further determine a first location associated with the audio data. The stored bird sound waveforms may be stored on the server itself or may be accessed from a separate database. The server may then generate information regarding the first bird species and the first location and transmit the information regarding the first bird species and the first location over the wide area network back to the user's device for presentation to the user. For example, the information may be useable to present the first bird species and the first location on a display of a user.
Some embodiments may also comprise a software application (software app) used for configuring a UE device, such as a smart phone or tablet (e.g., iPad) to perform various birdwatching operations as described herein. The software application may be stored on a non-transitory computer accessible memory medium comprising program instructions. The program instructions may be executable to cause the device to 1) receive audio data from a plurality of microphones, wherein the audio data corresponds to bird sounds of a bird and includes directional information indicating a location of the bird; 2) transmit the audio data to a server using a radio; 3) receive resultant information from the server indicating a first bird species of the bird and a first location of the bird, based on the transmitted audio data; and 4) display, on the display, a map of an area surrounding the microphone, and a first icon indicating the first location of the bird on the map.
This Summary is intended to provide a brief overview of some of the subject matter described in this document. Accordingly, it will be appreciated that the above-described features are merely examples and should not be construed to narrow the scope or spirit of the subject matter described herein in any way. Other features, aspects, and advantages of the subject matter described herein will become apparent from the following Detailed Description, Figures, and Claims.
A better understanding of the present invention may be obtained when the following detailed description of the preferred embodiment is considered in conjunction with the following drawings, in which:
While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and are herein described in detail. It should be understood, however, that the drawings and detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the intention is to cover all modifications, equivalents and alternatives falling within the spirit and scope of the present invention as defined by the appended claims.
The following is a glossary of terms used in the present application:
Auditory Sensor—Auditory Sensor is made up of one or more auditory sensors.
Video/Image Sensor—Video/Image Sensor is comprised of one or more video/image sensors. The Video/Image Sensor is not limited to only the human visible spectrum.
Other Sensor—Other Sensor is made up of one or more other (e.g. LIDAR) sensors.
Sensor Processing—Sensor Processing includes initial processing of data which may include organization of data to be transported to the Processing System.
Function Processing—Function Processing includes Pre-Processing, Main-Processing, and Post-Processing of the Function. Function Processing may include multiple pre-processing, processing, and post-processing sub-functions.
Immersive Experience Processing—Immersive Experience Processing is the combining of all the data to create a multidimensional organization of the data based on the sensor input to the system in preparation for supporting the human interface, delivery of data through a simple experience to a more complex augmented visualization experience or full virtual reality experience.
Birder Controlled Experience—Birder Controlled Experience is the human interface delivering the experience of the system to the Birder. This presentation experience device can be anything from a smart phone, tablet, to smart glasses to a full virtual reality multi-dimensional theater experience.
Locality of Processing and Database—Locality of Processing and Database data may include performing processing and access of database data on single device to across multiple devices to remote devices, e.g. cloud servers.
Embodiments of the directional birdwatching system described herein may operate to enhance the birdwatching experience of bird watchers, from the “Casual Birder” to the “Hard Core Birder”. This system intends to bring the wonder of the outdoors coupled with encyclopedic knowledge together to drive an interactive augmented or virtual reality experience for the Birder. The Birder may be fully in control of the Birder immersive experience. The experience can be enjoyed in various ways, including directly interactive with the environment, remotely experienced, or synthesized from recorded data. The system may be designed to support sharing and interactive socialization of the recorded data and experiences with the Birding community. Additionally, the system may be configured to become interactive with the environment being sensed, supporting actively tracking the object of interest to promoting interactivity with the object of interest.
As used herein, the term “backpack” is intended to include any of various types of bags that may be worn or carried, including standard backpacks worn over one or both shoulders, bags that may be worn across the waist (e.g., fanny packs), as well as other types of bags or containers that may be worn or carried. As shown in
The sensor assembly 112 may include a shaft (e.g., a pole) 132, wherein the term “shaft” refers to any extension apparatus. The shaft is used for extending sensors outside of the backpack. One end of the shaft 132 may include a sensor head or device 134 which may contain one or more sensors. The sensors may be at a distal end of the shaft, meaning that they are near or at one end of the shaft. The shaft 132 may be a telescoping pole (an extendable pole) whereby the user can selectively extend the shaft or pole 132 outside of the backpack to a desired height or distance. For example, the shaft 132 may be extended to a distance such that the sensor head 134 is outside of the backpack, and possible above the head of the birder, as shown in
The sensor head 134 may include one or more auditory sensors or microphones that are adapted to receive audio signals from the nearby environment, including sounds of birds (e.g., birdsong). The one or more microphones may comprise a plurality of directional microphones (a directional microphone array) for detecting an approximate orientation of objects generating sounds received by the microphones, e.g., for detecting directional locations of birds based on received bird sounds. For example, the sensor head may include a plurality of (an array of) directional microphones oriented in various directions such that sounds received by the microphones can be used to pinpoint an approximate direction, and hence location, of an object generating the sounds (e.g., the location of a bird). The sensor assembly 112 may also include one or more video sensors for receiving video data of the environment. The video cameras may be triggered to acquire video data in response to detection of bird audio data. In some embodiments, the antenna assembly may also include an antenna for performing wireless communication, such as a cellular antenna for communicating with a cellular base station. The sensor assembly 112 may further include speakers for generating sounds, such as bird sounds, to attract bird species of interest.
The processing/display system 114 may comprise a processing element (not shown) and other electronic components or circuitry. The processing system may be contained within a chassis or housing. In some embodiments, the processing system 114 may be part of the sensor assembly 112. In this embodiment the processing system 114 may be situated inside the backpack, e.g., where the backpack is used to hold the processing system, and possibly at least a portion of the sensor assembly, for convenience. In other words, the birder may wear or carry the backpack, where the backpack stores or holds at least a portion of the birder system. As noted above, the sensor(s), e.g., microphone(s), video sensor(s), etc., may be located remotely from the processor system, e.g., may be in the form of sensor(s) on or near the end of a shaft (e.g., telescopic pole) extending out of the backpack, where a lower portion of the shaft resides at least partly in the backpack or is strapped to the outside of the backpack. Alternatively, the processing/display system 114 may be situated outside of the backpack.
In a preferred embodiment, a user's existing user equipment (UE) device, such as a tablet, e.g., iPad or cellular smart phone device, may function as the processing/display system 114. The UE 114 may store and execute a software application (app) that configures the UE to perform various of the operations described herein. The UE 112 may be coupled to the sensor assembly 112 in a wired (or wireless) manner. The UE 112 includes a display device which displays various data acquired by the sensors on the sensor assembly, as described more in
The UE 112 (e.g., cell phone or iPad) may include cellular communication capability. As shown, the UE 112 may communicate in a wireless manner to a cellular base station 122, thereby enabling the UE 112 to communicate with a server (e.g., cloud server) 124. The UE 114 may provide the various sensor information to the cloud server 124, and the cloud server 124 may perform various processing functions on behalf of the birder system, such as identifying, locating and/or tracking birds detected by the sensors on the sensor assembly 112. The cloud server 124 can then provide this result information back to the UE 114 for presentation to the user. The use of cloud server 124 allows for a central repository for various bird songs, which can be updated regularly by the various birders using the server. The cloud server 124 may also facilitate the sharing of a birding experience over social media with other birders, possibly in real time as the bird watching experience is occurring. When the birder is in a more remote location without access to a nearby cell tower, the birder system may employ satellite communications to communicate with the cloud server 124.
In some embodiments, instead of using cloud server 124 for processing, the UE 112 performs most or all of the above processing locally, such as identifying, locating and/or tracking birds based on information provided by the sensors on the sensor assembly 112. In this embodiment, the cloud server may not be needed for real-time operation, and may be accessed primarily for updates as new bird songs are added to the cloud server repository and may be downloaded to the UE 114. Local processing may be desired in instances where the birder is in a remote location far from any cell towers or other communications equipment, and hence where access to a cloud server may not be possible or financially practical. In this scenario, the user may download a set of bird sounds and other bird species information associated with birds that are likely to be encountered on to his UE device for use while birdwatching.
In operation, the user (birder) may be walking in an environment carrying a backpack containing the birder system, as shown in
Alternatively, the audio signals received from the microphones on the sensor assembly 112 may be provided by the UE 114 to the cloud server 124. For example, the sensor assembly 112 may provide the audio signals to the user's UE device (cell phone or tablet), which may then transmit these audio signals wirelessly (e.g., in a cellular manner) to a cellular base station/cellular network 122 (or satellite), and then over the Internet to the cloud server 124.
In another embodiment, the birder system may include a processing system that is separate from the user's existing UE, which may include more sophisticated wireless communication capability that performs this function, using an antenna contained within the sensor assembly. This system may be desired in remote locations where greater transmit power is desired, e.g., for satellite communication. It is noted that use of the user's existing UE device may be preferred, as this leverages the user's existing processor, cellular electronics and antenna, thus providing reduced cost.
The cloud server 124 may store or have access to a repository (database) of different bird songs. The cloud server 124 may receive the audio signals from the birder system carried by the user and determine the type (or species) of bird that generated the sounds. For example, the cloud server 124 may compare (e.g., using correlation or convolution) the received audio signals with various stored bird song data and determine the best match, and hence determine the bird species that originated the sounds. In some embodiments, the cloud server 124 may use more advanced artificial intelligence (AI)/machine learning techniques to aid in identifying bird species based on the received audio signals as well as information regarding the geographic location of the user.
The cloud server 124 may also perform the location processing, e.g., may use the received audio signals from the directional antennas, as well as information regarding which directional antennas received the sounds, the strength of the sounds, etc. and may determine the approximate location of the bird which originated the sounds. In some embodiments, the cloud server 124 may receive audio and location information from two or more birders in the same geographic area and employ triangulation to aid in determining a more precise location of the bird.
The cloud server 124 may then provide the species information and location information back to the birder system (the UE 114). The UE 114 may receive the species information and location information and display this data on the UE's display. As noted above, the UE 114 may store and execute an application (app) that operates to perform the various functions described herein, including receiving and displaying this information.
The server 124 may also store birding experiences based on its processing of the received sensor data. The stored birding experience may include the bird sounds received and recorded by the microphones, video of the birds captured by video sensors (video cameras) on the sensor assembly, and determined location and species information. These birding experiences may be uploaded to social media or otherwise may be shareable with other birders, or may be recorded and re-played at a later time to recreate the experience for the user or other users. Thus one or more of the UE 114 or the server may store the detected bird audio signals and the resultant processed information (e.g., location and species) so that the experience can be shared on social media and/or re-played at a later time.
Each bird icon presented on the display may be selectable by the user to cause additional information regarding the bird species to be displayed. For example, the user may select an icon on the display to cause a picture of the bird species to be displayed and/or to cause information about the bird species to be displayed. Thus the birder system may also selectively display a prestored picture of the bird species as well as information regarding the species. The icon may also be selectable to cause pre-stored sounds of the bird species to be displayed, or to cause a recording of the bird sound that was just detected to be re-played to the user.
Movements of the bird(s) may also be tracked on the display. For example, when the microphone array detects movement of a bird to a different location, this new audio information may be received and processed, either locally (e.g., by the UE) or remotely (by the server), and new location information may be generated and provided to the UE. This may cause the display to present updated information on the bird's movements (the bird's location), as detected by the birder system or cloud server 124 based on updated information received by the sensors. Thus, the icon representing the bird may be moved to a new position on the display to represent the determined change in location of the bird.
The birder system is capable of processing a plurality of birds at the same time, and thus the user may see a corresponding plurality of icons on the display representing the various detected birds in the vicinity. The birder system is also capable of tracking a plurality of birds at the same time.
Thus, based on audio signals received by the microphone area on the sensor assembly 112, the location and identification of one or more birds may be determined, and information associated with the location and identification of one or more birds may be presented on the display.
In some embodiments, the birder system is capable of receiving information from other nearby birder systems regarding locations and species of birds in the proximate area. Thus, if one birder system detects a certain species of bird (such as a rare species), the system may be configured to broadcast this information (e.g., using a cellular transmission) to other birder systems in the area. This may cause each of the other birder systems to provide an alert to its respective user, and display an icon on their respective displays indicating the bird species, possibly on their maps. In some embodiments, where the bird detected by another system is too far away from the user to appear on his respective map as presently displayed, the other birder systems may cause their maps to “zoom out” so that the bird can appear on their respective display. This provides information to other users so that they can move closer to the detected species of bird for their own watching experience.
The following is an overview of the operation of a system in use by a birder. The system is able to identify bird related sounds in the environment, determine specie(s), and determine relative location of the specie(s), and track the specie(s) detected to the birder. The system is also able to document and record this information, including approximate absolute location. The presentation experience may be delivered via a handheld mobile device, known today as a tablet, whereby the birder may interactively bring up more information on the specie(s) detected. These findings and recordings may be shared socially with others electronically. The system can also provide a real-time enhanced hyper-sensory and/or surround sound auditory experience, or playback recorded or shared recorded experiences.
The birder system may also have the ability to reverse the process, i.e., the system may be used to actively stimulate the environment with auditory signals (to generate artificial bird sounds) to solicit a particular specie(s) response. More particularly, the sensor head 134 may also contain one or more speakers for generating bird sounds in order to attract nearby birds. The user may use his/her UE device to select one or more bird species for audio generation, wherein the UE may generate an audio waveform provided either by the birder system (or cloud server) that is output from the speaker to simulate presence of the bird species. In some embodiments, user selection of a particular bird species is transmitted to the cloud server 150, and the cloud server 150 provides the desired bird audio waveform back to the birder system for presentation on the speakers.
As shown, the SOC 300 may be coupled to various other circuits of the UE 114. For example, the UE 114 may include various types of memory (e.g., including flash 310), a connector interface 320 (e.g., for coupling to a computer system, dock, charging station, etc.), the display 360, and wireless communication circuitry 330 (e.g., for cellular, Bluetooth, Wi-Fi, GPS, etc.). The UE device 114 may include at least one antenna for performing wireless communication with base stations and/or other devices.
The UE 114 may include hardware and software components for implementing methods for the UE 114 to perform any of various of the bird watching operations described herein.
The processed sensor data may then be provided to a Function Processing block. In some embodiments, Function Processing may be performed locally on the processing system of the birder system. If Function Processing is not occurring locally, the processing system may perform packetization of the received sensor data for transmission of this data to the cloud server for processing.
The Function Processing, block may include multiple processing steps to convert the resulting sensor data received from the Sensor Processing block into data to be used by the Immersive Experience Processing block. The Function Processing block may include three steps referred to as Pre-processing, Main-processing, and Post-processing. The operation of the Function Processing block is broken out into three steps to potentially support the unique receiving and unpacking of sensor data, organization of data for Main processing, an iterative nature of some Main processing algorithms that may require data reorganization, and the different Locality of Processing and Database schemes. The following provides four different embodiments of the Function Processing operation.
The Function Processing 412 illustrates a straight-forward dataflow processing of the three steps, where Pre-processing is performed first, followed by Main-processing and then followed by Post-processing. The Function Processing 414 illustrates multiple subsystem function processing steps that are interactive with each other, potentially sharing or dependent on each result to produce a solution. The Function processing 416 illustrates the operation 412 described above with the addition of multiple feedback loops enabling iterative function processing. The Function processing 418 combines the algorithmic representation of 414 and 416. For the auditory sensor example there are potentially one or more Function Processing sub-systems that are operating in parallel.
As noted above, the birder system may operate to identify the species of the bird whose sound is detected. To support species identification, the Function Processing may implement one or more of correlation, convolution and/or deep learning/artificial intelligence techniques. The methods may involve comparing an acquired waveform of bird sound detected by the microphones to each of a plurality of stored waveforms representing different bird species. The correlation method may perform a correlation between the recorded bird sound and various stored bird sound waveforms, whereas the convolution method may perform a convolution between the recorded bird sound and various stored bird sound waveforms. Each processing architecture may be represented by 412 through 414 for a real-time implementation.
To support specie relative direction/location, space time frequency adaptive processing techniques may be used to facilitate a three-dimensional mapping of audio over time representation of the environment. To support tracking of the object or specie of interest, potentially predictive vector correlation and segmentation techniques based on the sounds shape in multi-multidimensional space can be used. Again, all of these subsystems and subsystems of subsystems can potentially be facilitated in a Function processing architecture represented by 412 through 416.
The Immersive Experience Processing block may prepare the raw result data from the Function block for delivery to the experience medium, e.g., a tablet such as an iPad. The experience medium may support various levels of interactivity. The processing may allow for complete or subset recording of the sensed environment and for simplification of content to address target experience. The processing may support interactivity with the experience, supporting changes in operational experience, delivery of ancillary content for the experience, etc. The resulting experience could be a simple notification, to augmented reality, to a full virtual reality system.
The Birder Controlled Experience is the Birder Interface in the context of an experience, where the features of the experience and its capabilities are directly and indirectly determined by the types of Sensors, Sensor Processing, and Function Processing the system supports. This enables a generic platform to potentially support many levels of features provided capabilities are available and enabled.
Additionally, guidance to specie(s) or unique experiences can be derived from the detection and tracking capabilities in the Birder's current experience or though social electronic interaction with other Birders real-time or past recorded and shared experiences.
The social network experience may provide for tracking and sharing of experiences in real-time and non-real-time, including species list, locations, etc.
The Directional Birdwatching System is not just limited to Birding but applicable to many species and objects of interest.
Although specific embodiments have been described above, these embodiments are not intended to limit the scope of the present disclosure, even where only a single embodiment is described with respect to a particular feature. Although the embodiments above have been described in considerable detail, numerous variations and modifications will become apparent to those skilled in the art once the above disclosure is fully appreciated. It is intended that the following claims be interpreted to embrace all such variations and modifications.
Examples of features provided in the disclosure are intended to be illustrative rather than restrictive unless stated otherwise. The above description is intended to cover such alternatives, modifications, and equivalents as would be apparent to a person skilled in the art having the benefit of this disclosure.
The scope of the present disclosure includes any feature or combination of features disclosed herein (either explicitly or implicitly), or any generalization thereof, whether or not it mitigates any or all of the problems addressed herein. Accordingly, new claims may be formulated during prosecution of this application (or an application claiming priority thereto) to any such combination of features. In particular, with reference to the appended claims, features from dependent claims may be combined with those of the independent claims and features from respective independent claims may be combined in any appropriate manner and not merely in the specific combinations enumerated in the appended claims.
This application claims benefit of priority to U.S. Provisional Application No. 62/809,852 titled “Directional Birdwatching System” and filed on Feb. 25, 2019 which is hereby incorporated by reference in its entirety as if fully and completely set forth herein.
Number | Date | Country | |
---|---|---|---|
62809852 | Feb 2019 | US |