Identifying regions of interest in an imaging field of view
The techniques described herein relate to computerized methods, systems and non-transitory computer-readable media for determining a plurality of regions of interest from an image of a scene for motion detection. The methods can include generating the regions of interest using image segmentation techniques and receiving user selection to designate one or more regions as motion detection zones. The methods can also automatically recommend motion detection zones. The methods can include subsequently capturing one or more images of a scene and performing motion detection in the one or more images of the scene using the designated motion detection zones.
1. A method, comprising:
receiving first pixel data corresponding to a first region within a field of view of a camera and second pixel data corresponding to a second region within the field of view;
determining that the first pixel data is indicative of a first event;
determining that first metadata associates the first region with a first form of delivery of an alert;
based at least in part on the first pixel data being indicative of the first event and the first metadata associating the first region with the first form of delivery, causing a first alert to be sent to an endpoint device using the first form of delivery;
determining that the second pixel data is indicative of a second event;
determining that second metadata associates the second region with a second form of delivery of an alert, wherein the second form of delivery is different than the first form of delivery; and
based at least in part on the second pixel data being indicative of the second event and the second metadata associating the second region with the second form of delivery, causing a second alert to be sent to the endpoint device using the second form of delivery.
2. The method of claim 1 , wherein:
causing the first alert to be sent to the endpoint device using the first form of delivery includes configuring the first alert to be output via a first application of the endpoint device; and
causing the second alert to be sent to the endpoint device using the second form of alert delivery includes configuring the second alert to be output via a second application of the endpoint device, wherein the second application is different from the first application.
3. The method of claim 2 , wherein:
the first application is a phone application; and
the second application is text message application.
4. The method of claim 1 , further comprising:
determining that the first metadata further associates the first region with a first timing of delivery of an alert; and
determining that the second metadata further associates the second region with a second timing of delivery of an alert;
wherein causing the first alert to be sent to the endpoint device further comprises, based at least in part on the first metadata associating the first region with the first timing of delivery, causing the first alert to be sent to the endpoint device immediately after determining that the first pixel data is indicative of the first event; and
wherein causing the second alert to be sent to the endpoint device further comprises, based at least in part on the second metadata associating the second region with the second timing of delivery, causing sending of the second alert to the endpoint device to be delayed after determining that the second pixel data is indicative of the second event.
5. The method of claim 1 , further comprising:
determining that the first metadata further associates the first region with one or more first monitoring parameters;
based at least in part on the first metadata associating the first region with the one or more first monitoring parameters, causing the first pixel data to be processed using the one or more first monitoring parameters to detect the first event;
determining that the second metadata further associates the second region with one or more second monitoring parameters, wherein the one or more second monitoring parameters are different than the one or more first monitoring parameters; and
based at least in part on the second metadata associating the second region with the one or more second monitoring parameters, causing the second pixel data to be processed using the one or more second monitoring parameters to detect the second event.
6. The method of claim 5 , wherein:
the one or more first monitoring parameters identify first windows of time during which the first pixel data is to be processed to detect events; and
the one or more second monitoring parameters identify second windows of time during which the second pixel data is to be processed to detect events, wherein the second windows of time are different than the first windows of time.
7. The method of claim 5 , wherein:
the one or more first monitoring parameters identify a first type of event that is to be detected based on the first pixel data; and
the one or more second monitoring parameters identify a second type of event that is to be detected based on the second pixel data, wherein the second type of event is different than the first type of event.
8. The method of claim 5 , wherein:
causing the first pixel data to be processed using the one or more first monitoring parameters further comprises sending the first pixel data to a remote computing system for processing; and
causing the second pixel data to be processed using the one or more second monitoring parameters further comprises sending the second pixel data to the remote computing system for processing.
9. The method of claim 8 , further comprising:
refraining from sending, to the remote computing system, third pixel data that is included an image together with the first pixel data or the second pixel data.
10. The method of claim 9 , further comprising:
sending, to the remote computing system, third metadata that identifies a relative position of the first pixel data or the second pixel data within the image.
11. The method of claim 8 , further comprising:
sending, to the remote computing system, the one or more first monitoring parameters to cause the remote computing system to process the first pixel data in accordance with the one or more first monitoring parameters; and
sending, to the remote computing system, the one or more second monitoring parameters to cause the remote computing system to process the second pixel data in accordance with the one or more second monitoring parameters.
12. The method of claim 8 , further comprising:
sending, to the remote computing system, a first indication that the first region is associated with the one or more first monitoring parameters to cause the remote computing system to process the first pixel data in accordance with the one or more first monitoring parameters; and
sending, to the remote computing system, a second indication that the second region is associated with the one or more second monitoring parameters to cause the remote computing system to process the second pixel data in accordance with the one or more second monitoring parameters.
13. The method of claim 1 , wherein:
the first event corresponds to detected motion within the first region; and
the second event corresponds to detected motion within the second region.
14. The method of claim 1 , further comprising:
determining, using an automated image analysis technique, a plurality of regions from an image of a scene, the plurality of regions including at least the first region and the second region;
displaying the plurality of regions;
receiving user selection of the first region and the second region from among the plurality of regions, wherein the user selection is indicative of the first region and the second region being designated as motion detection zones; and
storing first data designating the first region and the second region as motion detection zones for performing motion detection on one or more subsequent images acquired by the camera within the field of view.
15. The method of claim 14 , further comprising:
displaying information in association with respective ones of the plurality of regions that indicates likelihoods that the respective ones of the plurality of regions will be useful as motion detection zones.
16. The method of claim 15 , wherein the information that is displayed in association with the respective ones of the plurality of regions comprises respective score values or graphical representations associated with the respective ones of the plurality of regions.
17. The method of claim 14 , wherein determining the plurality of regions further comprises:
performing semantic segmentation on the image of the scene to segment the image into the plurality of regions.
18. A system, comprising:
one or more processors; and
one or more non-transitory computer-readable mediums encoded with instructions which, when executed by the one or more processors, cause the system to:
receive first pixel data corresponding to a first region within a field of view of a camera and second pixel data corresponding to a second region within the field of view;
determine that the first pixel data is indicative of a first event;
determine that first metadata associates the first region with a first timing of delivery of an alert;
based at least in part on the first pixel data being indicative of the first event and the first metadata associating the first region with the first timing of delivery, cause a first alert to be sent to an endpoint device in accordance with the first timing of delivery;
determine that the second pixel data is indicative of a second event;
determine that second metadata associates the second region with a second timing of delivery of an alert, wherein the second timing of delivery is different than the first timing of delivery; and
based at least in part on the second pixel data being indicative of the second event and the second metadata associating the second region with the second timing of delivery, cause a second alert to be sent to the endpoint device in accordance with the second timing of delivery.
19. The system of claim 18 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
cause the first alert to be sent to the endpoint device in accordance with the first timing of delivery at least in part by causing the first alert to be sent to the endpoint device immediately after determining that the first pixel data is indicative of the first event; and
cause the second alert to be sent to the endpoint device in accordance with the second timing of delivery at least in part by causing sending of the second alert to the endpoint device to be delayed after determining that the second pixel data is indicative of the second event.
20. The system of claim 18 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
determine that the first metadata further associates the first region with one or more first monitoring parameters;
based at least in part on the first metadata associating the first region with the one or more first monitoring parameters, cause the first pixel data to be processed using the one or more first monitoring parameters to detect the first event;
determine that the second metadata further associates the second region with one or more second monitoring parameters, wherein the one or more second monitoring parameters are different than the one or more first monitoring parameters; and
based at least in part on the second metadata associating the second region with the one or more second monitoring parameters, cause the second pixel data to be processed using the one or more second monitoring parameters to detect the second event.
21. The system of claim 20 , wherein:
the one or more first monitoring parameters identify first windows of time during which the first pixel data is to be processed to detect events; and
the one or more second monitoring parameters identify second windows of time during which the second pixel data is to be processed to detect events, wherein the second windows of time are different than the first windows of time.
22. The system of claim 20 , wherein:
the one or more first monitoring parameters identify a first type of event that is to be detected based on the first pixel data; and
the one or more second monitoring parameters identify a second type of event that is to be detected based on the second pixel data, wherein the second type of event is different than the first type of event.
23. The system of claim 20 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
cause the first pixel data to be processed using the one or more first monitoring parameters at least in part by sending the first pixel data to a remote computing system for processing; and
cause the second pixel data to be processed using the one or more second monitoring parameters at least in part by sending the second pixel data to the remote computing system for processing.
24. The system of claim 23 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
refrain from sending, to the remote computing system, third pixel data that is included an image together with the first pixel data or the second pixel data.
25. The system of claim 24 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
send, to the remote computing system, third metadata that identifies a relative position of the first pixel data or the second pixel data within the image.
26. The system of claim 23 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
send, to the remote computing system, the one or more first monitoring parameters to cause the remote computing system to process the first pixel data in accordance with the one or more first monitoring parameters; and
send, to the remote computing system, the one or more second monitoring parameters to cause the remote computing system to process the second pixel data in accordance with the one or more second monitoring parameters.
27. The system of claim 23 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
send, to the remote computing system, a first indication that the first region is associated with the one or more first monitoring parameters to cause the remote computing system to process the first pixel data in accordance with the one or more first monitoring parameters; and
send, to the remote computing system, a second indication that the second region is associated with the one or more second monitoring parameters to cause the remote computing system to process the second pixel data in accordance with the one or more second monitoring parameters.
28. The system of claim 18 , wherein:
the first event corresponds to detected motion within the first region; and
the second event corresponds to detected motion within the second region.
29. The system of claim 18 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
determine, using an automated image analysis technique, a plurality of regions from an image of a scene, the plurality of regions including at least the first region and the second region;
display the plurality of regions;
receive user selection of the first region and the second region from among the plurality of regions, wherein the user selection is indicative of the first region and the second region being designated as motion detection zones; and
store first data designating the first region and the second region as motion detection zones for performing motion detection on one or more subsequent images acquired by the camera within the field of view.
30. The system of claim 29 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
display information in association with respective ones of the plurality of regions that indicates likelihoods that the respective ones of the plurality of regions will be useful as motion detection zones.
31. The system of claim 30 , wherein the information that is displayed in association with the respective ones of the plurality of regions comprises respective score values or graphical representations associated with the respective ones of the plurality of regions.
32. The system of claim 18 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
determine that the first metadata further associates the first region with a first form of delivery of an alert; and
determining that the second metadata further associates the second region with a second form of delivery of an alert, the second form of delivery being different than the first form of delivery;
wherein causing the first alert to be sent to the endpoint device further comprises, based at least in part on the first metadata associating the first region with the first form of delivery, causing the first alert to be sent to the endpoint device using the first form of delivery; and
wherein causing the second alert to be sent to the endpoint device further comprises, based at least in part on the second metadata associating the second region with the second form of delivery, causing the second alert to be sent to the endpoint device using the second form of delivery.
33. The system of claim 32 , wherein the one or more non-transitory computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
cause the first alert to be sent to the endpoint device using the first form of delivery at least in part by configuring the first alert to be output via a first application of the endpoint device; and
cause the second alert to be sent to the endpoint device using the second form of delivery at least in part by configuring the second alert to be output via a second application of the endpoint device, wherein the second application is different from the first application.
34. The system of claim 33 , wherein:
the first application is a phone application; and
the second application is text message application.
35. A method, comprising:
receiving pixel data corresponding to different regions within a field of view of a camera, the different regions including at least a first region and a second region;
identifying a plurality of events based on the pixel data, the plurality of events including at least a first event based on first pixel data corresponding to the first region and a second event based on second pixel data corresponding to the second region;
determining a plurality of forms of delivery of alerts and/or timings of delivery of alerts based the different regions, the plurality of forms of delivery and/or timings of delivery including at least a first form of delivery and/or a first timing of delivery based on the first region and a second form of delivery and/or a second timing of delivery based on the second region; and
based at least in part on the plurality of events and plurality of forms of delivery and/or timings of delivery, causing a plurality of alerts to be sent to an endpoint device, the plurality of alerts including at least a first alert for the first event and a second alert for the second event, the first alert being sent to the endpoint device using first form of delivery and/or in accordance with the first timing of delivery and the second alert being sent to the endpoint device using the second form of delivery and/or in accordance with the second timing of delivery.