System, method and article of manufacture for tracking a head of a camera-generated image of a person

1. A method of tracking a head of a person image in video images comprising:

identifying an initial location of a point of separation between a torso portion and a head portion of the person image in the video images;

tracking a current location of the point of separation between the torso portion and the head portion of the person image starting at the initial location;

generating a confidence value representative of a confidence that the current location of the point of separation between the torso portion and the head portion of the person image in the video images is correct; and

identifying the initial location of the point of separation between the torso portion and the head portion of the person image upon each instance that the confidence value falls below a predetermined amount.

2. The method of claim 1 , wherein the initial location of the point of separation between the torso portion and the head portion of the person image is identified based on the detection of a skin color in the video images.

3. The method of claim 1 , wherein the current location of the point of separation between the torso portion and the head portion of the person image is tracked based on the detection of a skin color in the video images.

4. The method of claim 1 , wherein the initial location of the point of separation between the torso portion and the head portion of the person image is identified based on the detection of motion in the video images.

5. The method of claim 1 , wherein the current location of the point of separation between the torso portion and the head portion of the person image is tracked based on the detection of motion in the video images.

6. A computer program embodied on a computer readable medium for tracking a head of a person image in video images comprising:

a code segment for identifying an initial location of a point of separation between a torso portion and a head portion of the person image in the video images;

a code segment for tracking a current location of the point of separation between the torso portion and the head portion of the person image starting at the initial location;

a code segment for generating a confidence value representative of a confidence that the current location of the point of separation between the torso portion and the head portion of the person image in the video images is correct; and

a code segment for identifying the initial location of the point of separation between the torso portion and the head portion of the person image upon each instance that the confidence value falls below a predetermined amount.

7. A method of tracking a head of a person image in video images comprising:

identifying an initial location of a point of separation between a torso portion and a head portion of a person image in video images;

tracking a current location of the point of separation between the torso portion and the head portion of the person image starting at the initial location;

obtaining a flesh map while tracking the current location of the point of separation between the torso portion and the head portion of the person image; and

using the flesh map during subsequent identification of an initial location of the point of separation between the torso portion and the head portion of the person image.

8. A computer program embodied on a computer readable medium for tracking a point of separation between a torso portion and a head of a person image in video images comprising:

a code segment for identifying an initial location of the point of separation between the torso portion and the head portion of a person image in video images;

a code segment for tracking a current location of the point of separation between the torso portion and the head portion of the person image starting at the initial location;

a code segment for obtaining a flesh map while tracking the current location of the point of separation between the torso portion and the head portion of the person image; and

a code segment for using the flesh map during subsequent identification of a next initial location of a point of separation between the torso portion and the head portion of the person image.

9. A system for tracking a head portion of a person image in video images, comprising:

a receiver for receiving video images;

logic for executing a first head tracking operation for generating a first confidence value representative of a confidence that a head portion of a person image in the video images is located, the first head tracking operation comprising identifying a point of separation between a torso portion of the person image and the head portion of the person image;

logic for executing a second head tracking operation for generating a second confidence value representative of a confidence that the head portion of the person image in the video images is located; and

an output device for outputting the first confidence value and the second confidence value, wherein the depiction of the head portion of the person image in the video images is based on the first confidence value and the second confidence value.

10. The system of claim 9 , wherein the logic for executing the first head tracking operation tracks the head portion of the person image in the video images using previous video images including the head portion of the person image.

11. The system of claim 9 , wherein the logic for executing the first head tracking operation tracks the head portion of the person image in the video images using a mass distribution.

12. A system for tracking a head portion of a person image in video images, comprising:

a receiver for receiving video images;

logic for executing a first head tracking operation for generating a first confidence value representative of a confidence that a head portion of a person image in the video images is located;

logic for executing a second head tracking operation for generating a second confidence value representative of a confidence that the head portion of the person image in the video images is located; and

an output device for outputting the first confidence value and the second confidence value, wherein the depiction of the head portion of the person image in the video images is based on the first confidence value and the second confidence value; and

wherein the logic for executing the first head tracking operation subtracts a background image from the video images in order to extract the person image, generates a histogram representing the extracted person image, and identifies a point of separation between a torso portion of the person image and the head portion of the person image.

13. The system of claim 12 , wherein the logic for executing the first head tracking operation identifies a top of the head portion of the person image and the sides of the head portion of the person image.

14. The system of claim 13 , wherein the logic for executing the first head tracking operation identifies the top of the head portion of the person image by performing a search upwardly from the point of separation between the torso portion and the head portion of the person image.

15. The system of claim 9 , wherein the logic for executing the second head tracking operation identifies an initial location of the head portion of the person image in the video images and tracks a current location of the head portion of the person image starting at the initial location.

16. The system of claim 15 , wherein the logic for executing the second head tracking operation identifies the initial location of the head portion of the person image upon each instance that the second confidence value falls below a predetermined amount.

17. The system of claim 15 , wherein the logic for executing the second head tracking operation identifies the initial location of the head portion of the person image based on detecting a skin color in the video images.

18. The system of claim 17 , wherein the logic for executing the second head tracking operation identifies the initial location of the head portion of the person image by extracting a flesh map, filtering the flesh map, identifying distinct regions of flesh color on the flesh map, ranking the regions of flesh color on the flesh map, and selecting at least one of the regions of flesh color as the initial location of the head portion of the person image based on the ranking.

19. The system of claim 18 , wherein the logic for executing the second head tracking operation fills in holes in the regions of flesh color on the flesh map.

20. The system of claim 18 , wherein the logic for executing the second head tracking operation combines regions of flesh color on the flesh map based on a predetermined criterion.

21. The system of claim 15 , wherein the logic for executing the second head tracking operation tracks the current location of the head portion of the person image based on detecting a skin color in the video images.

22. The system of claim 21 , wherein the logic for executing the second head tracking operation tracks the current location of the head portion of the person image by extracting a sub-window of the head portion of the person image in the video images, forming a color model based on the sub-window, searching the video images for a color similar to the color model, and estimating the current location of the head portion of the person image based on the search.

23. The system of claim 15 , wherein the logic for executing the second head tracking operation identifies the initial location of the head portion of the person image based on detecting motion in the video images.

24. The system of claim 23 , wherein the logic for executing the second head tracking operation identifies the initial location of the head portion of the person image by creating a motion distribution map from the video images, generating a histogram based on the motion distribution map, identifying areas of motion using the histogram, and selecting at least one of the areas of motion as being the initial location of the head portion of the person image.

25. The system of claim 15 , wherein the logic for executing the second head tracking operation tracks the current location of the head portion of the person image based on detecting motion in the video images.

26. The system of claim 25 , wherein the logic for executing the second head tracking operation identifies the current location of the head portion of the person image by determining a search window based on a previous location of the head portion of the person image, creating a motion distribution map within the search window, generating a histogram based on the distribution motion map, identifying areas of motion using the histogram, and selecting at least one of the areas of motion as being the initial location of the head portion of the person image.

27. A system for tracking a head portion of a person image in video images, comprising:

a receiver for receiving video images;

a processor for executing a head tracking operation for generating a confidence value representative of a confidence that a head portion of a person image in the video images is located, the head tracking operation comprising identifying a point of separation between a torso portion of the person image and the head portion of the person image; and

a display for depicting the head portion of the person image in the video images based on the confidence value.