Single constraint at a time (SCAAT) tracking of a virtual reality (VR) display

• US 7,657,079 B2
• Filed: 06/28/2002
• Issued: 02/02/2010
• Est. Priority Date: 06/28/2002
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Lake, Adam T., Marshall, Carl S.
• Primary Examiner(s): TUCKER, WESLEY J
• Application Number:
  US10/185,577
• Publication Number:
  US 20040001647A1
• Time in Patent Office: 2,776 Days
• Field of Search: 382/154, 382/103, 382/285, 382/294
• US Class Current: 382/154
• CPC Class Codes: G06T 7/73 using feature-based methods

Abstract

A system to capture an image and determine a position of an object utilizes a camera. A first processing module recognizes a set of predetermined landmarks, including a first landmark and remainder landmarks, in the image. A second processing module determines an actual location of the first landmark in the image, and applies at least one filtering scheme to estimate positions of the remainder landmarks in the image. A third processing module determines a pose of the object based on the actual location of the first landmark and the estimated positions of the remainder landmarks.

Claims

1. A system to capture an image and determine a position of an object, comprising:

a hand-held personal digital assistant (PDA);

a camera communicatively coupled to the hand-held PDA to capture an image while the PDA is hand-held;

a first processing module to recognize a set of predetermined landmarks, including a first landmark and remainder landmarks, in the image;

a second processing module to determine an actual location of the first landmark in the image, the actual location of the first landmark representing a single constraint, and apply at least one filtering scheme to estimate positions of the remainder landmarks in the image based on the actual location of the first landmark representing the single constraint;

a third processing module to determine a pose of the object based on the actual location of the first landmark representing the single constraint and the estimated positions of the remainder landmarks; and

a rendering module to calculate a three-dimensional (3-D) representation of the image using the pose of the object based on the actual location of the first landmark representing the single constraint and the estimated positions of the remainder landmarks.

2. The system of claim 1, wherein the first, second, and third processing modules are all housed within an image processing device.

3. The system of claim 1, wherein the at least one filtering scheme includes application of a Kalman filter.

4. The system of claim 1, wherein the object is a user'"'"'s face.

5. The system of claim 1, wherein the object is the camera.

6. The system of claim 1, wherein the set of predetermined landmarks includes colored landmarks having a predetermined color.

7. The system of claim 1, wherein the set of predetermined landmarks includes shaped landmarks having a predetermined shape.

8. The system of claim 1, further including a display device to display the calculated 3-D representation of the image.

9. An apparatus to determine a position of an object, comprising:

a Hand-held personal digital assistant (PDA);

a reception device communicatively coupled to the hand-held PDA to receive an image while the PDA is hand-held;

a first processing module to recognize a set of predetermined landmarks, including a first landmark and remainder landmarks, in the image;

a second processing module to determine an actual location of the first landmark in the image, the actual location of the first landmark representing a single constraint, and apply at least one filtering scheme to estimate positions of the remainder landmarks in the image based on the actual location of the first landmark representing the single constraint;

a third processing module to determine a pose of the object based on the actual location of the first landmark representing the single constraint and the estimated positions of the remainder landmarks, and

a rendering module to calculate a three-dimensional (3-D) representation of the image using the pose of the object based on the actual location of the first landmark representing the single constraint and the estimated positions of the remainder landmarks.

10. The apparatus of claim 9, wherein the first, second, and third processing modules are all housed within an image processing device.

11. The apparatus of claim 9, wherein the at least one filtering scheme includes application of a Kalman filter.

12. The apparatus of claim 9, wherein the object is a user'"'"'s face.

13. The apparatus of claim 9, wherein the object is the Hand-held personal digital assistant (PDA).

14. The apparatus of claim 9, wherein the set of predetermined landmarks includes colored landmarks having a predetermined color.

15. The apparatus of claim 9, wherein the set of predetermined landmarks includes shaped landmarks having a predetermined shape.

16. The apparatus of claim 9, further including a display device to display the calculated 3-D representation of the image.

17. A method to determine a position of an object, comprising:

capturing an image using a reception device communicatively coupled to a Hand-held personal digital assistant (PDA) while the PDA is hand-held;

recognizing a set of predetermined landmarks, including a first landmark and remainder landmarks, in the image;

determining an actual location of the first landmark in the image, the actual location of the first landmark representing a single constraint;

applying at least one filtering scheme to estimate positions of the remainder landmarks in the image based on the actual location of the first landmark representing the single constraint;

determining a pose of the object based on the actual location of the first landmark representing the single constraint and the estimated positions of the remainder landmarks, and

calculating a three-dimensional (3-D) representation of the image using the pose of the object based on the actual location of the first landmark representing the single constraint and the estimated positions of the remainder landmarks.

18. The method according to claim 17, wherein the at least one filtering scheme includes application of a Kalman filter.

19. The method according to claim 17, wherein the object is a user'"'"'s face.

20. The method according to claim 17, wherein the object is a camera.

21. The method according to claim 17, wherein the set of predetermined landmarks includes colored landmarks having a predetermined color.

22. The method according to claim 17, wherein the set of predetermined landmarks includes shaped landmarks having a predetermined shape.

23. The method according to claim 17, further including displaying the calculated 3-D representation of the image.

24. The method according to claim 17, further including:

capturing a subsequent image;

determining an actual location of a second landmark; and

estimating positions of the first landmark and the remainder landmarks other than the second landmark.

25. An article comprising:

a storage medium having stored thereon instructions that when executed by a machine result in the following;

capturing an image using a reception device communicatively coupled to a Hand-held personal digital assistant (PDA), while the PDA is hand-held;

recognizing a set of predetermined landmarks, including a first landmark and remainder landmarks, in the image;

determining an actual location of the first landmark in the image, the actual location of the first landmark representing a single constraint;

applying at least one filtering scheme to estimate positions of the remainder landmarks in the image based on the actual location of the first landmark representing the single constraint;

determining a pose of an object based on the actual location of the first landmark representing the single constraint and the estimated positions of the remainder landmarks, and

calculating a three-dimensional (3-D) representation of the image using the pose of the object based on the actual location of the first landmark representing the single constraint and the estimated positions of the remainder landmarks.

26. The article according to claim 25, wherein the at least one filtering scheme includes application of a Kalman filter.

27. The article according to claim 25, wherein the object is a user'"'"'s face.

28. The article according to claim 25, wherein the object is the Hand-held personal digital assistant (PDA).

29. The article according to claim 25, wherein the set of predetermined landmarks includes colored landmarks having a predetermined color.

30. The article according to claim 25, wherein the set of predetermined landmarks includes shaped landmarks having a predetermined shape.

31. The article according to claim 25, wherein the instructions further result in displaying the calculated 3-D representation of the image.

32. The article according to claim 25, wherein the instructions further result in:

capturing a subsequent image;

determining an actual location of a second landmark; and

estimating positions of the first landmark and the remainder landmarks other than the second landmark.