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 method comprising:
tracking, by an electronic device, objects using hyperzooms generated by the electronic device while obviating network usage by the electronic device;
generating tracks of the objects based on the tracking, wherein the hyperzooms are removed from the electronic device;
generating track metadata from the tracks for storing in a key-value database located on the electronic device wherein the tracks are removed from the electronic device;
receiving a query specifying a characteristic of the objects;
generating a response to the query by filtering the track metadata using the characteristic;
generating a heatmap using the track metadata; and
displaying the response and a graphical representation of the heatmap on a screen of a computer device.
2. The method of claim 1 , comprising:
generating a visualization of the tracks; and
storing, by the electronic device, the tracks and the visualization in a key-value structure on cloud storage, the visualization for sending to a user device.
3. The method of claim 1 , wherein the key-value database stores the tracks as byte arrays on a non-transitory computer-readable storage medium.
4. The method of claim 1 , wherein the key-value database stores the tracks in immutable row partitions in sorted order.
5. The method of claim 1 , wherein the key-value database stores the tracks in a relational database management system (RDBMS) on a non-transitory computer-readable storage medium.
6. The method of claim 1 , comprising:
assigning identifiers to the objects in a first hyperzoom; and
responsive to detecting the objects in a second hyperzoom:
propagating identifiers in the second hyperzoom; and
associating the second hyperzoom with the objects.
7. A camera comprising:
a non-transitory computer-readable storage medium; and
a computer processor communicably coupled to the non-transitory computer-readable storage medium and configured to:
track objects using hyperzooms generated by the camera while obviating network usage by the camera;
generate tracks of the objects based on the tracking, wherein the hyperzooms are removed from the camera;
generate track metadata from the tracks for storing in a key-value database located on the non-transitory computer-readable storage medium, wherein the tracks are removed from the camera;
receive a query specifying a characteristic of the objects;
generate a response to the query by filtering the track metadata using the characteristic;
generate a heatmap using the track metadata; and
transmit the response and a graphical representation of the heatmap for display on a screen of a computer device.
8. The camera of claim 7 , wherein the computer processor is configured to:
generate a visualization of the tracks; and
store the tracks and the visualization in a key-value structure on cloud storage, the visualization for sending to a user device.
9. The camera of claim 7 , wherein the computer processor is configured to:
generate the hyperzooms from image frames captured by the camera, the hyperzooms comprising a first hyperzoom and a second hyperzoom, the first hyperzoom associated with the objects.
10. The camera of claim 9 , wherein the computer processor is configured to:
detect the objects in the second hyperzoom; and
update positions of the objects based on detecting the objects in the second hyperzoom, wherein the first hyperzoom and the second hyperzoom are removed from the camera.
11. The camera of claim 7 , wherein the key-valued database stores the tracks in one of byte arrays on the non-transitory computer-readable storage medium, immutable row partitions in sorted order, or a relational database management system (RDBMS) on the non-transitory computer-readable storage medium.
12. The camera of claim 7 , wherein the computer processor is configured to:
assign identifiers to the objects in a first hyperzoom; and
responsive to detecting the objects in a second hyperzoom:
persist identifiers in the second hyperzoom; and
associate the second hyperzoom with the objects.
13. A system comprising:
one or more computer processors; and
a non-transitory computer-readable storage medium storing computer instructions, which when executed by the one or more computer processors cause the one or more computer processors to:
track, by an electronic device, objects using hyperzooms generated by the electronic device while obviating network usage by the electronic device;
generate tracks of the objects based on the tracking, wherein the hyperzooms are removed from the electronic device;
generate track metadata from the tracks for storing in a key-value database located on the electronic device wherein the tracks are removed from the electronic device;
receive a query specifying a characteristic of the objects;
generate a response to the query by filtering the track metadata using the characteristic;
generate a heatmap using the track metadata; and
display the response and a graphical representation of the heatmap on a screen of a computer device.
14. The system of claim 13 , wherein the computer instructions cause the one or more computer processors to:
generate a visualization of the tracks; and
store the tracks and the visualization in a NoSQL key-value structure on cloud storage, the visualization for sending to a user device.
15. The system of claim 13 , wherein the computer instructions cause the one or more computer processors to:
generate the hyperzooms from image frames captured by the electronic device, the hyperzooms comprising a first hyperzoom and a second hyperzoom, a first hyperzoom associated with the objects.
16. The system of claim 15 , wherein the computer instructions cause the one or more computer processors to:
detect the objects in the second hyperzoom; and
update positions of the objects based on detecting the objects in the second hyperzoom, wherein the first hyperzoom and the second hyperzoom are removed from the electronic device.
17. The system of claim 13 , wherein the key-value database stores the tracks in one of byte arrays on the electronic device, immutable row partitions in sorted order, or a relational database management system (RDBMS) on the electronic device.