Balanced template tracker for tracking an object image sequence

• US 6,445,832 B1
• Filed: 10/10/2000
• Issued: 09/03/2002
• Est. Priority Date: 10/10/2000
• Status: Expired due to Term

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Lee, Harry C., Nguyen, Dat
• Primary Examiner(s): Patel, Jayanti K.
• Application Number:
  US09/684,817
• Time in Patent Office: 693 Days
• Field of Search: 382/100, 382/103, 382/173, 382/181, 382/190, 382/199, 382/203, 382/236, 382/215-221, 382/266, 382/269, 382/283, 382/291, 382/284, 348/458, 709/247, 345/449
• US Class Current: 382/266
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image

Abstract

A method and apparatus are described for tracking an object image in an image sequence in which a template window associated with the object image is established from a first image in the image sequence and an edge gradient direction extracted. A search window associated with the object image is established from a second image in the image sequence and a second edge gradient direction associated with the search window extracted. The first and second edge gradient directions are weighted and correlated to provide a coordinate offset between relative positions of the object image in the search and template windows to track the object image in the image sequence. If the coordinate offset exceeds a predetermined value the template window is updated by establishing a new template window. Weighting further includes calculating a set of weighting coefficients for the edge gradient direction associated with the search window and the template window respectively such that a balanced contribution is provided from respective edge gradient directions in correlation. The edge direction gradient associated with the template window is auto-correlated to determine a quality measure. Extracting the second edge gradient direction further includes I filtering the second edge gradient direction and an edge magnitude, thinning the second edge gradient direction, thresholding the edge magnitude, and normalizing the second edge gradient direction if the edge magnitude is successfully thresholded.

Claims

1. A method for tracking an object image in an image sequence, the method comprising:

establishing a template window associated with the object image from a first image in the image sequence and extracting a first edge gradient direction associated with the template window;

establishing a search window associated with the object image from a second image in the image sequence and extracting a second edge gradient direction associated with the search window;

weighting the first and second edge gradient directions; and

correlating the first and second edge gradient directions to track the object image over one or more images in the image sequence.

2. The method of claim 1, wherein the step of correlating further includes the step of providing a coordinate offset between a position of the object image in the search window and a position of the object image in the template window.

3. The method of claim 2, further including the step of updating the template window by establishing a new template window if the coordinate offset exceeds a predetermined value.

4. The method of claim 1, wherein the step of weighting further includes the step of calculating a set of weighting coefficients for the edge gradient direction associated with the search window and the template window respectively such that a balanced contribution is provided from edge gradient directions associated with the search window and the template window in the step of correlating.

5. The method of claim 1, further including the step of auto-correlating the edge direction gradient associated with the template window to determine a quality measure associated with the template window prior to the step of correlating.

6. The method of claim 1, wherein the step of extracting the second edge gradient direction associated with the search window further includes the steps of:

sobel filtering the second edge gradient direction and an edge magnitude associated therewith;

thinning the second edge gradient direction;

thresholding the associated edge magnitude; and

normalizing the second edge gradient direction if the associated edge magnitude is successfully thresholded.

7. An apparatus for tracking an object image, the apparatus comprising:

an image sequence;

a processor for receiving the image sequence, the processor configured to;

establish a template window associated with the object image from a first image in the image sequence and extracting a first edge gradient direction associated with the template window;

establish a search window associated with the object image from a second image in the image sequence and extracting a second edge gradient direction associated with the search window;

weight the first and second edge gradient directions; and

correlate the first and second edge gradient directions to track the object image over one or more images in the image sequence.

8. The apparatus of claim 7, wherein the processor, in correlating, is further configured to provide a coordinate offset between a position of the object image in the search window and a position of the object image in the template window.

9. The apparatus of claim 8, wherein the processor is further configured to update the template window by establishing a new template window if the coordinate offset exceeds a predetermined value.

10. The apparatus of claim 7, wherein the processor, in weighting, is further configured to calculate a set of weighting coefficients for the edge gradient direction associated with the search window and the template window respectively such that a balanced contribution is provided from edge gradient directions associated with the search window and the template window in correlating.

11. The apparatus of claim 7, wherein the processor is further configured to auto-correlate the edge direction gradient associated with the template window to determine a quality measure associated with the template window prior to the step of correlating.

12. The apparatus of claim 7, wherein the processor, in extracting the second edge gradient direction associated with the search window, is further configured to:

sobel filter the second edge gradient direction and an edge magnitude associated therewith;

thin the second edge gradient direction;

threshold the associated edge magnitude; and

normalize the second edge gradient direction if the associated edge magnitude is successfully thresholded.