Systems, methods, apparatuses, and devices for radar-based identifying, tracking, and managing of unmanned aerial vehicles
Systems, methods, and apparatus for identifying and tracking UAVs including a plurality of sensors operatively connected over a network to a configuration of software and/or hardware. A computing device can receive the data for the plurality of tracks from a data store. The computing device can perform an evaluation of each of the plurality of tracks based on the data for the plurality of tracks. The computing device can assign at least one camera to a particular track of the plurality of tracks based on the evaluation.
1 . A system, comprising:
a data store comprising data for a plurality of tracks; and
at least one computing device in communication with the data store, wherein the at least one computing device is configured to:
receive the data for the plurality of tracks from the data store;
perform an evaluation of each of the plurality of tracks based on the data for the plurality of tracks, wherein performing the evaluation of each of the plurality of tracks comprises determining a respective time spent on track for each of the plurality of tracks; and
assign at least one camera to a particular track of the plurality of tracks based on the respective time spent on track for each of the plurality of tracks.
2 . The system of claim 1 , wherein the at least one computing device is further configured to perform the evaluation of each of the plurality of tracks by determining user-selected priority of at least one of the plurality of tracks for visual verification.
3 . The system of claim 1 , wherein the at least one computing device is further configured to perform the evaluation of each of the plurality of tracks by:
determining whether each of the plurality of tracks is unverified; and
prioritizing a subset of the plurality of tracks that are determined as being unverified.
4 . The system of claim 1 , wherein the at least one computing device is further configured to perform the evaluation of each of the plurality of tracks by:
determining a respective uncertainty value associated with a respective predicted position for each of the plurality of tracks; and
prioritizing a subset of the plurality of tracks based on the respective uncertainty value associated with the subset of the plurality of tracks.
5 . The system of claim 4 , wherein the respective uncertainty value is based on a proximity of the respective predicted position to a respective track head for each of the plurality of tracks.
6 . The system of claim 4 , wherein the respective uncertainty value for each of the plurality of tracks comprises a respective aggregated confidence level.
7 . The system of claim 6 , wherein the at least one computing device is further configured to determine whether the respective aggregated confidence level exceeds a predefined threshold.
8 . A non-transitory computer-readable medium embodying a program that, when executed by at least one computing device, causes the at least one computing device to:
receive data for a plurality of tracks;
perform an evaluation of each of the plurality of tracks based on the data for the plurality of tracks, wherein performing the evaluation of each of the plurality of tracks comprises determining a respective time spent on track for each of the plurality of tracks; and
assign at least one camera to a particular track of the plurality of tracks based on the respective time spent on track for each of the plurality of tracks.
9 . The non-transitory computer-readable medium of claim 8 , wherein the at least one camera comprises a pan, tilt, and zoom (“PTZ”) camera.
10 . The non-transitory computer-readable medium of claim 8 , wherein the program further causes the at least one computing device to perform the evaluation of each of the plurality of tracks by:
determining a respective uncertainty value associated with a respective predicted position for each of the plurality of tracks; and
prioritizing a subset of the plurality of tracks based on the respective uncertainty value associated with the subset of the plurality of tracks.
11 . The non-transitory computer-readable medium of claim 10 , wherein the respective uncertainty value is determined by applying a Kalman filter to determine a variance between the respective predicted position and a model of plausible track positions.
12 . The non-transitory computer-readable medium of claim 10 , wherein the respective uncertainty value is determined by calculating a standard deviation based on position measurements for each of a plurality of sensors.
13 . The non-transitory computer-readable medium of claim 8 wherein the program further causes the at least one computing device to perform the evaluation of each of the plurality of tracks by determining a respective proximity of each of the plurality of tracks to the at least one camera, wherein the at least one camera is assigned based on comparing the respective proximity of each of the plurality of tracks to an optimal range of the at least one camera.
14 . The non-transitory computer-readable medium of claim 8 , wherein the program further causes the at least one computing device to perform the evaluation of each of the plurality of tracks by determining that the particular track is above a threshold elevation, wherein the at least one camera is assigned to the particular track based on the at least one camera having a highest zoom capability than at least one other camera.
15 . A method, comprising:
receiving, via at least one computing device, data for a plurality of tracks from a memory device;
performing, via the at least one computing device, an evaluation of each of the plurality of tracks based on the data for the plurality of tracks, wherein performing the evaluation of each of the plurality of tracks comprises determining a respective time spent on track for each of the plurality of tracks; and
assigning, via the at least one computing device, at least one camera to a particular track of the plurality of tracks based on the respective time spent on track for each of the plurality of tracks.
16 . The method of claim 15 , further comprising:
receiving, via the at least one computing device, a video frame from the at least one camera; and
applying, via the at least one computing device, an object detection algorithm to the video frame.
17 . The method of claim 16 , further comprising:
identifying, via the at least one computing device, a particular unmanned aerial vehicle (UAV) based on applying the object detection algorithm to the video frame; and
moving, via the at least one computing device, the at least one camera to center on the particular UAV.
18 . The method of claim 16 , wherein the object detection algorithm comprises a neural network trained for identifying an unmanned aerial vehicle (UAV) in an airspace.
19 . The method of claim 18 , further comprising training the neural network using a first set of frames known to contain at least one UAV and a second set of frames known to contain at least one erroneously identified UAV.