Method and apparatus for tracking an object

• US 7,657,059 B2
• Filed: 08/08/2003
• Issued: 02/02/2010
• Est. Priority Date: 08/08/2003
• Status: Active Grant

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Lee, Harry, Stanfill, Robert, Cannon, Jamie, Slaski, James Joseph, Sefcik, Jason, Olson, Teresa Lorae Pace
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): Motsinger; Sean
• Application Number:
  US10/636,763
• Publication Number:
  US 20050031165A1
• Time in Patent Office: 2,370 Days
• Field of Search: 382/103, 382/107, 348/169, 348/170, 348/171, 348/172, 342/64, 342/52, 342/55, 342/62, 244/3.15, 244/3.16, 244/3.17
• US Class Current: 382/103
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51

Abstract

A method and apparatus for tracking an object in an image. An image of a scene comprising an object is received. The image is processed with a first tracker to produce a first estimate of a position of the object in the image and a first confidence value. The image is processed with a second tracker to produce a second estimate of the position of the object in the image and a second confidence value. The second tracker processes the image concurrently with the first tracker. An estimate of the position of the object in the image is selected using the first and second confidence values. The object is then tracked using the selected estimate.

Claims

1. A method of tracking an object comprising:

receiving an image of a scene, the scene comprising the object;

processing the image with a plurality of trackers to produce an estimate of a position of the object, wherein the processing comprises;

processing the image with a first tracker to produce a first estimate of the position of the object in the image and an associated first confidence value, and

processing the image with a second tracker, concurrently with the first tracker, to produce a second estimate of the position of the object in the image and an associated second confidence value, the second tracker processing the image using one or more of a plurality of processing techniques, wherein the second tracker selects which of the processing techniques are used based upon a distance between the object and a device comprising the first and second trackers;

selecting one of the produced estimates of the position of the object in the image using the first and second confidence values; and

tracking the object using the selected estimate.

2. The method of claim 1 further comprising:

processing the image to produce a third estimate of the position of the object in the image, wherein selecting one of the produced estimates includes selecting the third estimate based on a comparison of the first and second confidence values to a predetermined threshold.

3. The method of claim 2, further comprising:

segmenting the image to produce a fourth estimate of the position of the object in the image and an estimate of a size of the object in the image; and

providing the fourth estimate of the position and the estimate of the size to the first or second tracker based upon the first and second confidence values, respectively.

4. The method of claim 3, wherein the fourth estimate is used by the first or second tracker to reinitialize its tracking of the object in the image.

5. The method of claim 1, wherein the step of tracking the object comprises:

providing the selected estimate to a control system; and

adjusting parameters of the control system based on the selected estimate.

6. The method of claim 1, wherein the plurality of processing techniques includes a first processing technique that is an unresolved target tracking technique.

7. The method of claim 6, wherein the unresolved tracking technique tracks a single pixel in the image.

8. The method of claim 6, wherein the plurality of processing techniques includes a second processing technique that is a frame-to-frame correlation technique.

9. The method of claim 6, wherein the plurality of processing techniques includes a third processing technique that is a reference template-to-search region correlation process employing a gradient magnitude image.

10. The method of claim 1, wherein the first tracker tracks the object based upon components extracted from the image.

11. The method of claim 10, wherein the components are groups of pixels that have a same gradient direction and are connected along horizontal or vertical pixel edges.

27. The method of claim 1, wherein the second tracker is configured to process the image using a plurality of different processing techniques.

12. A system comprising:

a plurality of trackers to produce an estimate of a position of an object in an image, the plurality of trackers comprising;

a primary tracker which processes the image and outputs a first estimate of the position of the object in the image and an associated first confidence value; and

a secondary tracker which processes the image, concurrently with the primary tracker, and outputs a second estimate of the position of the object in the image and an associated second confidence value, the secondary tracker processing the image using one or more of a plurality of processing techniques, wherein the secondary tracker selects which of the processing techniques are used based upon a distance between the object and the system; and

an output selector processing circuitry which selects one of the outputted estimates of the position of the object in the image using the first and second confidence values.

13. The system of claim 12, further comprising:

a third tracker which processes the image and outputs a third estimate of the position of the object, wherein the output selector selects the third estimate based on a comparison of the first and second confidence values to a predetermined threshold.

14. The system of claim 13, further comprising:

an object selector which receives the image and outputs a fourth estimate of the position of the object in the image, a size of the object in the image, and a fourth confidence value, wherein the fourth estimate of the position and the size of the object are provided to the primary or secondary tracker based on the first and second confidence values, respectively.

15. The system of claim 12, wherein the secondary tracker comprises:

a first secondary tracker that processes the image using a first processing technique of the plurality of processing techniques;

a second secondary tracker that processes the image using a second processing technique of the plurality of processing techniques; and

a third secondary tracker that processes the image using a third processing technique of the plurality of processing techniques, wherein whether the first, second or third secondary tracker outputs the second estimate is based on the distance between the system and the object.

16. The system of claim 15, wherein the first secondary tracker uses an unresolved target tracking technique which tracks a single pixel in the image.

17. The system of claim 15, wherein the second secondary tracker uses a frame-to-frame correlation tracking technique.

18. The system of claim 15, wherein the third secondary tracker uses a reference template-to-search region correlation tracking technique which employs a gradient magnitude image.

19. The system of claim 12, wherein the primary tracker tracks the object based upon components extracted from the image, wherein the components are groups of pixels that have a same gradient direction and are connected along horizontal or vertical pixel edges.

28. The system of claim 12, wherein the secondary tracker is configured to process the image using a plurality of different processing techniques.

20. A system comprising:

a plurality of trackers, comprising;

a primary tracker that processes an image and outputs a first estimate of a position of an object in the image and an associated first confidence value, and

a secondary tracker that processes the image, concurrently with the first tracker, and outputs a second estimate of the position of the object in the image and an associated second confidence value, the secondary tracker processing the image using one or more of a plurality of processing techniques, wherein the secondary tracker selects which of the processing techniques are used based on a distance between the system and the object;

an output selector processing circuitry which selects one of the first and the second estimates of the position of the object in the image using the first and second confidence values when the first and second confidence values are above a predetermined threshold; and

a third tracker which receives the image and outputs a third estimate of the position of the object in the image, wherein the output selector selects the third estimate when the first and second confidence values are below the predetermined threshold.

21. The system of claim 20, further comprising:

an object selector which receives the image and outputs a fourth estimate of the position of the object in the image and a size of the object in the image, wherein when the first or second confidence values are below the predetermined threshold for a predetermined amount of time, the fourth estimate of the position and the size of the object are provided to the primary or secondary tracker based on the first and second confidence values, respectively.

22. The system of claim 20, wherein the secondary tracker comprises:

a first secondary tracker that processes the image using a first processing technique of the plurality of processing techniques;

a second secondary tracker that processes the image using a second processing technique of the plurality of processing techniques; and

a third secondary tracker that processes the image using a third processing technique of the plurality of processing techniques, wherein whether the first, second or third secondary tracker outputs the second estimate is based one the distance between the system and the object.

23. The system of claim 22, wherein the first secondary tracker uses an unresolved target tracking technique which tracks a single pixel in the image.

24. The system of claim 22, wherein the second secondary tracker uses a frame-to-frame correlation tracking technique.

25. The system of claim 22, wherein the third secondary tracker uses a reference template-to-search region correlation tracking technique which employs a gradient magnitude image.

26. The system of claim 20, wherein the primary tracker tracks the object based upon components extracted from the image, wherein the components are groups of pixels that have a same gradient direction and are connected along horizontal or vertical pixel edges.

29. The system of claim 20, wherein the secondary tracker is configured to process the image using a plurality of different processing techniques.