Target tracking in a multi-camera surveillance system

Patent metadata

Field	Value
Publication number	US-11258985-B2
Application number	US-201715477294-A
Country	US
Kind code	B2
Filing date	Apr 3, 2017
Priority date	Apr 5, 2016
Publication date	Feb 22, 2022
Grant date	Feb 22, 2022

Abstract

Tracking of targets in video captured by a multi-camera surveillance system is often difficult due to incomplete camera coverage and due to the complexities associated with automated recognition in a dense and highly variable environment. The present disclosure embraces a system and method for target tracking in a multi-camera surveillance system that reduces the time required for a user to track a target by offering computer generated search results that include suggestions of candidates found in the video that match (to some degree) the target. When one of the candidates is selected by a user, the search is shifted to other cameras and continued. In this way, the target may be tracked quickly. Further, a playlist of video snippets of the target is accumulated during the search and can be played to show all captured video of the target moving about the facility.

First claim

The invention claimed is:

1. A method for tracking a target in a multi-camera surveillance system, the method comprising:
receiving a primary camera selection, wherein the primary camera selection designates one camera from a plurality of cameras as primary;
assigning, based on the primary camera selection, secondary cameras that view areas different from primary camera;
receiving primary video from the primary camera and secondary video from the secondary cameras;
presenting the received primary video in a first window of a graphical user interface;
presenting the received secondary video in a second window of the graphical user interface;
upon observation of the target in displayed video by a user, selecting a portion of video as a target sample from a portion of the primary video, the target sample selected by the user;
adding the portion of video of the target sample to a target-sample set specific to the target;
presenting the target sample in a third window of the graphical user interface;
searching the secondary video for candidate samples based on the portions of video in the target sample set, wherein the candidate samples are portions of video from the secondary cameras;
presenting the portions of video of the candidate samples in the third window of the graphical user interface adjacent to the target sample;
upon determination by a user that at least one of the candidate samples includes the target, creating a new target sample from the at least one of the candidate samples, the at least one of the candidate samples associated with one of the secondary cameras;
automatically assigning the one of the secondary cameras as a new primary camera and automatically assigning, based on the one of the secondary cameras, new secondary cameras that view areas different from the one of the secondary cameras;
adding the new target sample to the target-sample set;
presenting the target samples of the target-sample set in the third window of the graphical user interface, wherein the target samples replace the portions of video of the candidate samples in the third window;
repeating the steps of searching, presenting, creating, updating, and adding until no candidate sample that includes the target is determined for a period;
obtaining geographic locations of cameras used to acquire the target samples in the target sample set;
obtaining times of the target samples in the target sample set; and
reconstructing, using the times and the geographic locations, a track of the target, wherein the track graphically depicts a path of the target through the geographical locations at the obtained times.

2. The method according to claim 1 , further comprising:
creating a video playlist of video from the portions of video in the target sample set arranged in chronological order.

3. The method according to claim 1 , wherein the primary video and the secondary video are live video and the tracking occurs in real time while the target is moving.

4. The method according to claim 1 , wherein the primary video and the secondary video are recorded video and the tracking occurs after the target has moved.

5. The method according to claim 1 , wherein the assigning, based on the primary camera selection, secondary cameras that view areas different from primary camera, comprises:
selecting cameras from the plurality of cameras that are proximate to the primary camera.

6. The method according to claim 1 , wherein the assigning, based on the primary camera selection, secondary cameras that view areas different from primary camera, comprises:
selecting cameras that have a likelihood of viewing the target after the target leaves the area viewed by the primary camera.

7. The method according to claim 6 , wherein the likelihood is determined by previous tracking.

8. The method according to claim 6 , wherein the likelihood is determined by previous camera selection by a user.

9. The method according to claim 1 , wherein the video from the secondary cameras are displayed in the second window of the graphical user interface according to the likelihood of the target appearing.

10. The method according to claim 1 , wherein the assigning, based on the primary camera selection, secondary cameras that view areas different from primary camera is automatic.

11. The method according to claim 10 , wherein the automatic selection uses heuristics based on previous searches.

12. The method according to claim 1 , wherein the candidate samples provide associated information when selected.

13. The method according to claim 12 , wherein the associated information comprises an indication of the camera that created a respective candidate sample.

14. The method according to claim 12 , wherein the associated information comprises an indication of the time a respective candidate sample was created.

15. The method according to claim 12 , wherein the associated information comprises a view of a respective candidate sample that is larger or higher resolution than provided initially.

16. The method according to claim 1 , wherein the assigning, based on the primary camera selection, secondary cameras that view areas different from primary camera, comprises:
selecting cameras within a specified range from the primary camera.

17. The method according to claim 1 , wherein the assigning, based on the primary camera selection, secondary cameras that view areas different from primary camera, comprises:
selecting cameras within along a route including the primary camera.

18. A multi-camera surveillance system, comprising:
a plurality of cameras that each capture video of different areas of a facility;
a central computing device communicatively coupled to the plurality of cameras, wherein the central computing device comprises a processor, the processor configured by software to:
receive a primary camera selection, wherein the primary camera selection designates one camera from a plurality of cameras as primary;
assign, based on the primary camera selection, secondary cameras that view areas different from primary camera;
receive primary video from the primary camera and secondary video from the secondary cameras;
present the received primary video in a first window of a graphical user interface;
present the received secondary video in a second window of the graphical user interface;
upon observation of the target in displayed video by a user, select a portion of video as a target sample from a portion of the primary video, the target sample selected by the user;
add the portion of video of the target sample to a target-sample set specific to the target;
present the target sample in a third window of the graphical user interface;
search the secondary video for candidate samples based on the portions of video in the target sample set, wherein the candidate samples are portions of video from the secondary;
present the portions of video of the candidate samples in the third window of the graphical user interface adjacent to the target sample;
upon determination by a user that at least one of the candidate samples includes the target, create a new target sample from the at least one of the candidate samples, the at least one of the candidate samples associated with one of the secondary cameras;
automatically assign the one of the secondary cameras as a new primary camera and automatically assigning, based on the one of the secondary cameras, new secondary cameras that view areas different from the one of the secondary cameras;
add the new target sample to the target-sample set;
p

Assignees

• Verint Americas Inc
• Verint Systems Inc

Inventors

• Johnson Alexander Steven
• Naor Nir
• Ostrovsky-Berman Yaron
• Figov Zvi

Classifications

• G11B27/105

  of operating discs · CPC title

• H04N7/181 Primary

  for receiving images from a plurality of remote sources · CPC title

• G06T7/292

  Multi-camera tracking · CPC title

• G06T2207/10024

  Color image · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title