Method And System For Metadata Extraction From Master-Slave Cameras Tracking System

• US 20140139680A1
• Filed: 11/20/2012
• Published: 05/22/2014
• Est. Priority Date: 11/20/2012
• Status: Active Grant

• Current Assignee: Pelco (Schneider Electric SE)
• Original Assignee: Pelco (Schneider Electric SE)
• Inventors: Huang, Chien-Min, Aghdasi, Farzin, Zhu, Hongwei, Wang, Lei, Ma, Zhan Jiang
• Granted Patent: US 9,210,385 B2
• Time in Patent Office: Days
• US Class Current: 348/159
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G08B 13/19608 Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
• CPC Class Codes: G08B 13/19643 wherein the cameras play different roles, e.g. different resolution, different camera type, master-slave camera
• CPC Class Codes: G08B 13/19671 Addition of non-video data, i.e. metadata, to video stream
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

An embodiment of the present invention includes a master camera that may record master metadata regarding an object of interest and communicate the master metadata to a slave camera. The slave camera may zoom, pan, or tilt to isolate and record more detailed image data regarding the object of interest based on the master metadata. In addition, the slave camera may record slave metadata regarding the object of interest. The master and slave metadata may be stored associated with the recorded image data enabling a later search for the object of interest to be expedited. The recorded image data including the object of interest may be identified with greater ease as it may be guided by the master or slave metadata, or a combination thereof. According to embodiments presented herein, processing time for searching and identifying an object of interest may be reduced by enabling a search on the metadata associated with image data, rather than by searching the image data itself.

Claims

1. A method of enabling retrieval of information from a video surveillance system, the method comprising:

automatically identifying an object of interest in a video scene of a master camera or a slave camera, the object of interest for the slave camera being determined as a function of metadata from the master camera;

automatically classifying at least one feature in the object of interest; and

storing a representation of the at least one feature in a form of metadata, including the metadata from the master camera to the slave camera, associated with video of at least the slave camera in a manner enabling retrieval of information about the object of interest.

2. The method according to claim 1, wherein the metadata further includes slave metadata associated with the object identified.

3. The method according to claim 1, wherein retrieval is more efficient on average via the metadata than via direct observation of the video.

4. The method according to claim 1, wherein identifying an object of interest includes applying background subtraction to remove background objects from the video scene.

5. The method according to claim 1, wherein the metadata further includes slave metadata associated with the object identified, the method of claim 1 further including tracking the object of interest by adjusting the slave camera'"'"'s field of view based on object information included in the metadata from the master camera.

6. The method according to claim 5 wherein adjusting the slave camera'"'"'s field of view includes zooming in on the object of interest and following movement of the object of interest.

7. The method according to claim 5, wherein the slave metadata includes a start time stamp indicating a start time of the slave camera'"'"'s tracking the object and an end time stamp indicating an end time of the slave camera'"'"'s tracking the object.

8. The method according to claim 5, wherein adjusting the slave camera'"'"'s field of view is further based on processing the video scene at the slave camera based on the object information from the master camera and wherein the slave metadata includes detailed object information extracted from the video scene by the slave camera.

9. The method according to claim 8, wherein processing the video scene includes searching of one or more image frames of the slave camera captured during tracking, the searching being based on the object information included in the metadata from the master camera and the slave camera.

10. The method according to claim 5, wherein adjusting the slave camera'"'"'s field of view includes directing the slave camera to a pan and tilt position, the method according to claim 5 further including:

analyzing one or more image frames of the slave camera during tracking;

extracting detailed object information from the one or more image frames; and

storing the detailed object information extracted as the slave metadata.

11. The method according to claim 1, wherein automatically classifying at least one feature in the object of interest includes categorizing the object of interest as a person, vehicle, or animal.

12. The method according to claim 1, wherein automatically classifying at least one feature in the object of interest includes classifying movement of the object identified as stationary or moving, wherein a moving classification further includes an estimated rate of movement of the object identified.

13. The method according to claim 1, wherein the metadata includes a time stamp, identified color, identified license plate number, aspect ratio, or bounding box for the object of interest.

14. The method according to claim 1, wherein the form of metadata further includes slave metadata associated with the object identified, the method of claim 1 further including storing the metadata on a server.

15. The method according to claim 1, wherein automatically identifying the object of interest, automatically classifying at least one feature in the object of interest, and storing the representation of the at least one feature in the form of metadata occur during recording of the video scene.

16. The method according to claim 1, wherein automatically identifying the object of interest, automatically classifying at least one feature in the object of interest, and storing the representation of the at least one feature in the form of metadata occur after recording of the video scene.

17. The method according to claim 1, wherein the form of metadata further includes slave metadata associated with the object identified, the method of claim 1 further including presenting the form of metadata of the object identified to a user.

18. A system for enabling retrieval of information from a video surveillance system, the system comprising:

a master camera, a slave camera, and a server communicatively coupled;

the master camera configured to identify an object of interest automatically in a video scene of the master camera or the slave camera and to communicate master classification information of the object identified in the form of metadata to the slave and to the server;

the slave camera configured to determine more detailed slave classification information based on the master classification information communicated and to communicate the more detailed slave classification information in the form of metadata to the server; and

the server configured to store the master classification information and the detailed slave classification information in a manner enabling retrieval of information about the object of interest.

19. The system of claim 18, wherein the slave camera is further configured to communicate the more detailed slave classification information in the form of metadata to the master camera or an indication that the master classification information communicated is incorrect.

20. The system of claim 18, wherein the master camera is further configured to include a master bounding box for the video scene in the form of metadata and the slave camera is further configured to define a slave bounding box for the video scene based on the master bounding box, the more detailed slave classification information being based on data of the video scene within the slave bounding box.

21. The system of claim 20 wherein the slave camera defines the slave bounding box as a function of metadata from the master and its own processor.

22. The system of claim 21 wherein the master metadata includes data of a master bounding box and the slave camera uses data of objects within the master bounding box.

23. A method of enabling retrieval of information from a video surveillance system, the method comprising:

presenting a representation of at least one feature in an object of interest in a form of metadata from a master camera and a slave camera in a manner enabling retrieval of information about the object of interest.

24. The method of claim 23, wherein the metadata from the master camera includes classification information about the object of interest and the metadata from the slave camera includes more detailed classification information about the object of interest.