COORDINATION OF OBJECT LOCATION DATA WITH VIDEO DATA

• US 20150286865A1
• Filed: 04/08/2014
• Published: 10/08/2015
• Est. Priority Date: 04/08/2014
• Status: Abandoned Application

• Current Assignee: Sony Interactive Entertainment LLC (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.), Sony Network Entertainment International LLC (Sony Group Corp.)
• Inventors: MCCOY, Charles, XIONG, True
• Application Number:
  US14/247,615
• Publication Number:
  US 20150286865A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• 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: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 2201/10 Recognition assisted with metadata

Abstract

An object tracking system automatically generates metadata about locations of objects within a scene. The objects may then be associated with one or more objects within the scene.

Claims

1. An object tracking system comprising:

a sensor system detecting information about a scene;

an analysis unit analyzing the information to identify objects and location thereof within the scene, wherein the analysis unit determines an association of one object with at least one other object;

a processor generating metadata identifying each object location; and

tracking unit tracking object movement of the associated objects based on the generated metadata identifying each object location.

2. The object tracking system according to claim 1, wherein the information contains video data and the metadata for each object is inserted into the video data.

3. The object tracking system according to claim 1, wherein the sensor system includes sensors sensing visual and non-visual data.

4. The object tracking system according to claim 1, wherein the sensor system includes at least one sensor detecting at least radio frequency signals.

5. The object tracking system according to claim 1, wherein the sensor system includes at least one sensor detecting at least temperatures.

6. The object tracking system according to claim 1, wherein the tracking unit tracks the movement of objects over time based upon the metadata identifying each object location.

7. The object tracking system according to claim 6, farther comprising a mapping unit which draws a line on a map to map each identified objects'"'"' movement over time.

8. The object tracking system according to claim 1, wherein the analysis unit further analyzes metadata of objects to determine if two or more objects arc associated with one another by being within a predetermined distance of one another over a predetermined period of time.

9. The object tacking system according to claim 1, wherein the objects that are associated with one another include people and personal and non-personal items.

10. The object tracking system according to claim 1, wherein the analysis unit determines if detected objects are present in both of two consecutive video frames.

11. The object tracking system according to claim 10, wherein if objects are not previously tracked, video frames in which new objects appear are highlighted.

12. The object tracking system according to claim 1, further comprising an inserter inserting metadata into information about the scene, the metadata including the determined object association.

13. The object tracking system according to claim 1, wherein the analysis unit determines if objects are associated with one another by correlations in the movements of the objects based upon identifying each object location.

14. The object tracking system according to claim 10, wherein if an object which is being tracked is no longer detected, video frames are highlighted when the object is no longer detected.

15. A method of tracking objects comprising the steps of:

detecting information about a scene;

analyzing the information to identify objects and location thereof within a scene, including determining an association of one object with at least one other object;

generating metadata identifying each object location; and

tracking movement of the associated objects based on the generated metadata identifying each object location.

16. The method according to claim 15, wherein the information detected is video data and the metadata for each object is inserted into the video data.

17. The method according to claim 15, wherein the detection of information is by sensors sensing visual and non-visual data.

18. The method according to claim 17, wherein the sensors include sensors detecting at least radio frequency signals.

19. The method according to claim 15, wherein the metadata identifying each object location is for tracking the movement of objects over time.

20. The method according to claim 19, further comprising the steps of drawing a line on a map to map each identified objects'"'"' movement over time.

21. The method according to claim 15, further comprising the step of analyzing metadata to determine if two or more objects are associated with one another by being within a predetermined distance of one another over a predetermined period of time.

22. The method according to claim 15, wherein the objects that are associated with one another include people and personal and non-personal items.

23. The method according to claim 15, further comprising the step of determining if detected objects are present in both of two consecutives video frames.

24. The method according to claim 23, wherein if objects are not previously tracked, video frames in which new objects appear are highlighted.

25. The method according to claim 15, further comprising the step of predicting relationships between objects based on analyzing the metadata and statistically identifying relationships therebetween.

26. The method according to claim 15, further comprising the step of categorizing a plurality of associations of objects and associating a particular object with at least one other particular object based on statistical analysis of the categorization.

27. The method according to claim 15, further comprising the step or inserting metadata into the information about the scene, the metadata including the determined object association.

28. The method according to claim 17, wherein the detection of information is by sensors detecting at least temperatures.

29. The method according to claim 15, further comprising the step of determining if objects are associated with one another by correlations in movement of the objects based upon identifying each object location.

30. The method according to claim 23, wherein if an object which is being tracked is no longer detected, video frames are highlighted when the object is no longer detected.