People and vehicle analytics on the edge
A computer vision processor of a camera generates hyperzooms for persons or vehicles from image frames captured by the camera. The hyperzooms include a first hyperzoom associated with the persons or vehicles. The computer vision processor tracks traffic patterns of the persons or vehicles while obviating network usage by the camera by predicting positions of the persons or vehicles using a Kalman Filter from the first hyperzoom. The persons or vehicles are detected in the second hyperzoom. The positions of the persons or vehicles are updated based on detecting the persons or vehicles in the second hyperzoom. The first hyperzoom is removed from the camera. Tracks of the persons or vehicles are generated based on the updated positions. The second hyperzoom is removed from the camera. Track metadata is generated from the tracks for storing in a key-value database located on a non-transitory computer-readable storage medium of the camera.
1. A computer-implemented method comprising:
capturing image frames by a plurality of electronic devices;
generating hyperzooms, by the plurality of electronic devices, for objects in the image frames while obviating network usage by the plurality of electronic devices,
wherein each of the plurality of electronic devices generates a hyperzoom for at least one object detected by another of the plurality of electronic devices;
generating tracks of the objects, based on the hyperzooms, by comparing detected characteristics of the objects across the hyperzooms;
generating a graphical representation based on the tracks of the objects on a screen of a computer device;
searching, in response to a user input, across the plurality of electronic devices for additional information about the objects; and
displaying the additional information within the graphical representation on the screen of the computer device,
wherein the additional information about the objects corresponds to the user input.
2. The computer-implemented method of claim 1 , wherein the additional information comprises object analytics or an identification of all detected objects across the plurality of electronic devices.
3. The computer-implemented method of claim 1 , wherein the objects are detected using a neural network or a support vector machine.
4. The computer-implemented method of claim 1 , wherein the additional information comprises an alert corresponding to an object of interest.
5. A computer system comprising:
a plurality of computer processors; and
a non-transitory, computer-readable storage medium storing computer instructions, which when executed by the plurality of computer processors cause the computer system to:
capture image frames by a plurality of electronic devices;
generate hyperzooms, by the plurality of electronic devices, for objects in the image frames while obviating network usage by the plurality of electronic devices;
generate a graphical representation based on the objects on a screen of a computer device;
search, in response to a user input, across the plurality of electronic devices for additional information about the objects; and
display the additional information within the graphical representation on the screen of the computer device,
wherein the additional information about the objects corresponds to the user input.
6. The computer system of claim 5 , wherein the additional information comprises object analytics or an identification of all detected objects across the plurality of electronic devices.
7. The computer system of claim 5 , wherein the objects are detected using a neural network or a support vector machine.
8. The computer system of claim 5 , wherein the additional information comprises an alert corresponding to an object of interest.
9. The computer system of claim 5 , wherein the plurality of computer processors corresponds to the plurality of electronic devices.
10. The computer system of claim 5 , wherein each of the plurality of electronic devices generates a hyperzoom for at least one object detected by another of the plurality of electronic devices.
11. The computer system of claim 5 , wherein the computer instructions cause the computer system to generate tracks of the objects, based on the hyperzooms, by comparing detected characteristics of the objects across the hyperzooms,
wherein the graphical representation is based on the tracks of the objects.
12. The computer system of claim 5 , wherein each of the plurality of computer processors is a computer vision processor embedded in a corresponding one of the plurality of electronic devices.
13. A non-transitory, computer-readable storage medium storing computer instructions, which when executed by a plurality of computer processors of a computer system cause the computer system to:
capture image frames by a plurality of electronic devices;
generate hyperzooms, by the plurality of electronic devices, for objects in the image frames while obviating network usage by the plurality of electronic devices;
generate a graphical representation based on the objects on a screen of a computer device;
search, in response to a user input, across the plurality of electronic devices for additional information about the objects; and
display the additional information within the graphical representation on the screen of the computer device,
wherein the additional information about the objects corresponds to the user input.
14. The non-transitory, computer-readable storage medium of claim 13 , wherein the additional information comprises object analytics or an identification of all detected objects across the plurality of electronic devices.
15. The non-transitory, computer-readable storage medium of claim 13 , wherein the objects are detected using a neural network or a support vector machine.
16. The non-transitory, computer-readable storage medium of claim 13 , wherein the additional information comprises an alert corresponding to an object of interest.
17. The non-transitory, computer-readable storage medium of claim 13 , wherein the plurality of computer processors corresponds to the plurality of electronic devices.
18. The non-transitory, computer-readable storage medium of claim 13 , wherein each of the plurality of electronic devices generates a hyperzoom for at least one object detected by another of the plurality of electronic devices.
19. The non-transitory, computer-readable storage medium of claim 13 , wherein the computer instructions cause the computer system to generate tracks of the objects, based on the hyperzooms, by comparing detected characteristics of the objects across the hyperzooms,
wherein the graphical representation is based on the tracks of the objects.
20. The computer system of claim 13 , wherein each of the plurality of computer processors is a computer vision processor embedded in a corresponding one of the plurality of electronic devices.