Methods and systems of determining costs for object tracking in video analytics

• US 10,026,193 B2
• Filed: 08/05/2016
• Issued: 07/17/2018
• Est. Priority Date: 05/24/2016
• Status: Expired due to Fees

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Gao, Jinglun, Bi, Ning, Chen, Ying, Wang, Lei
• Primary Examiner(s): WOLDEMARIAM, AKLILU K
• Application Number:
  US15/229,456
• Publication Number:
  US 20170345179A1
• Time in Patent Office: 711 Days
• Field of Search: 382103, 382106, 382201, 382209, 382173, 348143
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes

Abstract

Techniques and systems are provided for processing video data. For example, techniques and systems are provided for determining costs for blob trackers and blobs. A blob can be detected in a video frame. The blob includes pixels of at least a portion of a foreground object. A physical distance between a blob tracker and the blob can be determined. A size ratio between the blob tracker and the blob can also be determined. A cost between the blob tracker and the blob can then be determined using the physical distance and the size ratio. In some cases, a spatial relationship between the blob tracker and the blob is determined, in which case the physical distance can be determined based on the spatial relationship. Blob trackers can be associated with blobs based on the determined costs between the blob trackers and the blobs.

Claims

1. A method of determining costs between blob trackers and blobs, the method comprising:

detecting a blob in a video frame, wherein the blob includes pixels of at least a portion of a foreground object in the video frame;

determining a spatial relationship between a blob tracker and the blob, the spatial relationship including an overlap between the blob tracker and the blob in at least one or more of a first dimension or a second dimension;

determining a physical distance between the blob tracker and the blob based on the spatial relationship, wherein calculation of the physical distance depends on whether the blob tracker and the blob overlap in the first dimension, in the second dimension, or in both the first dimension and the second dimension; and

determining a cost between the blob tracker and the blob using the physical distance, wherein the costs between the blob trackers and the blobs are used to associate one or more of the blob trackers with one or more of the blobs.

2. The method of claim 1, wherein the spatial relationship includes an overlap between the blob tracker and the blob in at least one or more of a first dimension or a second dimension, and wherein calculation of the physical distance depends on whether the blob tracker and the blob overlap in the first dimension, in the second dimension, or in both the first dimension and the second dimension.

3. The method of claim 2, wherein the spatial relationship includes an overlap between the blob tracker and the blob in the first dimension and the second dimension.

4. The method of claim 3, wherein determining the physical distance between the blob tracker and the blob includes:

determining a negative distance between the blob tracker and the blob based on the spatial relationship including the overlap between the blob tracker and the blob in the first dimension and the second dimension.

5. The method of claim 4, wherein the negative distance includes a comparison between an area of intersection of the blob tracker and the blob and an area of union of the blob tracker and the blob.

6. The method of claim 2, wherein determining the physical distance between the blob tracker and the blob includes:

determining a minimum distance in the first dimension between the blob tracker and the blob, wherein the minimum distance in the first dimension is determined when the spatial relationship includes an overlap between the blob tracker and the blob in the second dimension and no overlap between the blob tracker and the blob in the first dimension.

7. The method of claim 2, wherein determining the physical distance between the blob tracker and the blob includes:

determining a minimum distance in the second dimension between the blob tracker and the blob, wherein the minimum distance in the second dimension is determined when the spatial relationship includes an overlap between the blob tracker and the blob in the first dimension and no overlap between the blob tracker and the blob in the second dimension.

8. The method of claim 1, further comprising:

determining a size ratio between the blob tracker and the blob; and

wherein determining the cost for the blob tracker and the blob includes weighting the physical distance by the size ratio.

9. The method of claim 8, wherein the size ratio includes a comparison between an area of a tracker bounding box associated with the blob tracker and an area of a blob bounding box associated with the blob.

10. An apparatus comprising:

a memory configured to store video data; and

a processor configured to;

detect a blob in a video frame, wherein the blob includes pixels of at least a portion of a foreground object in the video frame;

determine a spatial relationship between a blob tracker and the blob, the spatial relationship including an overlap between the blob tracker and the blob in at least one or more of a first dimension or a second dimension;

determine a physical distance between the blob tracker and the blob based on the spatial relationship, wherein calculation of the physical distance depends on whether the blob tracker and the blob overlap in the first dimension, in the second dimension, or in both the first dimension and the second dimension; and

determine a cost between the blob tracker and the blob using the physical distance, wherein costs between blob trackers and blobs are used to associate one or more of the blob trackers with one or more of the blobs.

11. The apparatus of claim 10, wherein the processor is further configured to associate the blob tracker with the blob based on the determined cost.

12. The apparatus of claim 10, wherein the spatial relationship includes an overlap between the blob tracker and the blob in the first dimension and the second dimension.

13. The apparatus of claim 12, wherein determining the physical distance between the blob tracker and the blob includes:

determining a negative distance between the blob tracker and the blob based on the spatial relationship including the overlap between the blob tracker and the blob in the first dimension and the second dimension.

14. The apparatus of claim 13, wherein the negative distance includes a comparison between an area of intersection of the blob tracker and the blob and an area of union of the blob tracker and the blob.

15. The apparatus of claim 10, wherein determining the physical distance between the blob tracker and the blob includes:

determining a minimum distance in the first dimension between the blob tracker and the blob, wherein the minimum distance in the first dimension is determined when the spatial relationship includes an overlap between the blob tracker and the blob in the second dimension and no overlap between the blob tracker and the blob in the first dimension.

16. The apparatus of claim 10, wherein determining the physical distance between the blob tracker and the blob includes:

determining a minimum distance in the second dimension between the blob tracker and the blob, wherein the minimum distance in the second dimension is determined when the spatial relationship includes an overlap between the blob tracker and the blob in the first dimension and no overlap between the blob tracker and the blob in the second dimension.

17. The apparatus of claim 10, further comprising:

determining a size ratio between the blob tracker and the blob; and

wherein determining the cost for the blob tracker and the blob includes weighting the physical distance by the size ratio.

18. The apparatus of claim 17, wherein the size ratio includes a comparison between an area of a tracker bounding box associated with the blob tracker and an area of a blob bounding box associated with the blob.

19. The apparatus of claim 10, further comprising a camera configured to capture the video data.

20. The apparatus of claim 10, further comprising a network interface configured to communicate the video data.

21. The apparatus of claim 20, wherein the network interface is configured to communicate Internet Protocol (IP) based data.

22. A computer readable medium having stored thereon instructions that, when executed by one or more processors, cause the one or more processor to:

detect a blob in a video frame, wherein the blob includes pixels of at least a portion of a foreground object in the video frame;

determine a spatial relationship between a blob tracker and the blob, the spatial relationship including an overlap between the blob tracker and the blob in at least one or more of a first dimension or a second dimension;

determine a physical distance between the blob tracker and the blob based on the spatial relationship, wherein calculation of the physical distance depends on whether the blob tracker and the blob overlap in the first dimension, in the second dimension, or in both the first dimension and the second dimension; and

determine a cost between the blob tracker and the blob using the physical distance, wherein costs between blob trackers and blobs are used to associate one or more of the blob trackers with one or more of the blobs.

23. The computer readable medium of claim 22, further comprising instructions that, when executed by the one or more processors, cause the one or more processors to associate the blob tracker with the blob based on the determined cost.

24. The computer readable medium of claim 22, wherein the spatial relationship includes an overlap between the blob tracker and the blob in the first dimension and the second dimension.

25. The computer readable medium of claim 24, wherein determining the physical distance between the blob tracker and the blob includes:

determining a negative distance between the blob tracker and the blob based on the spatial relationship including the overlap between the blob tracker and the blob in the first dimension and the second dimension.

26. The computer readable medium of claim 22, wherein determining the physical distance between the blob tracker and the blob includes:

determining a minimum distance in the first dimension between the blob tracker and the blob, wherein the minimum distance in the first dimension is determined when the spatial relationship includes an overlap between the blob tracker and the blob in the second dimension and no overlap between the blob tracker and the blob in the first dimension.

27. The computer readable medium of claim 22, further comprising instructions that, when executed by the one or more processors, cause the one or more processors to:

determine a size ratio between the blob tracker and the blob; and

wherein determining the cost for the blob tracker and the blob includes weighting the physical distance by the size ratio.