System and method for feature location and tracking in multiple dimensions including depth

• US 7,050,624 B2
• Filed: 07/24/2001
• Issued: 05/23/2006
• Est. Priority Date: 12/04/1998
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Nevengineering Incorporated (Alphabet Inc.)
• Inventors: Dialameh, Orang, Neven, Hartmut
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US09/915,204
• Publication Number:
  US 20020031253A1
• Time in Patent Office: 1,764 Days
• Field of Search: 382/103, 382/115, 382/118, 382/154, 382/181, 382/190, 382/209, 382/276, 382/240, 382/281, 345/419, 348/169
• US Class Current: 382/154
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: H04N 13/239 using two 2D image sensors having a relative position equal to or related to the interocular distance H04N13/243 takes precedence
• CPC Class Codes: H04N 13/246 Calibration of cameras
• CPC Class Codes: H04N 13/302 for viewing without the aid of special glasses, i.e. using autostereoscopic displays
• CPC Class Codes: H04N 13/366 using viewer tracking
• CPC Class Codes: H04N 2013/0081 Depth or disparity estimation from stereoscopic image signals

Abstract

The present invention is directed to a method and related system for determining a feature location in multiple dimensions including depth. The method includes providing left and right camera images of the feature and locating the feature in the left camera image and in the right camera image using bunch graph matching. The feature location is determined in multiple dimensions including depth based on the feature locations in the left camera image and the right camera image.

Claims

1. A method for determining a feature location, comprising:

providing left and right camera images of the feature;

locating the feature in the left camera image and in the right camera image using bunch graph matching, wherein the feature is an eye of a person'"'"'s face; and

determining the feature location in multiple dimensions including depth based on the feature locations in the left camera image and the right camera image.

2. A method for determining a feature location, comprising:

providing left and right camera images of the feature;

locating the feature in the left camera image and in the right camera image using image analysis based on wavelet component values generated from wavelet transformations of the camera images, wherein the feature is an eye of a person'"'"'s face; and

determining the feature location in multiple dimensions including depth based on the feature locations in the left camera image and the right camera image.

3. A method for determining a feature location as defined in claim 2, wherein the wavelet transformations use Gabor wavelets.

4. Apparatus for determining a feature location, comprising:

means for providing left and right camera images of the feature;

means for locating the feature in the left camera image and in the right camera image using image analysis based on wavelet component values generated from wavelet transformations of the camera images, wherein the feature is an eye of a person'"'"'s face; and

means for determining the feature location in multiple dimensions including depth based on the feature locations in the left camera image and the right camera image.

5. Apparatus for determining a feature location as defined in claim 4, wherein the wavelet transformations use Gabor wavelets.

6. A method for determining a feature location, comprising:

providing first and second spaced-apart camera images of the feature;

locating the feature in the first camera image using image analysis based on wavelet component values generated from wavelet transformations of the first camera image, wherein the feature is an eye of a person'"'"'s face; and

locating the feature in the second camera image using image analysis based on wavelet component values generated from wavelet transformations of the second camera image; and

determining the feature location in multiple dimensions including depth based on the feature location in the first camera image and the feature location in the second camera image.

7. A method for determining a feature location as defined in claim 6, wherein the wavelet transformations use Gabor wavelets.

8. Apparatus for determining a feature location, comprising:

means for providing left and right camera images of the feature;

means for locating the feature in the left camera image and in the right camera image using bunch graph matching, wherein the feature is an eye of a person'"'"'s face; and

means for determining the feature location in multiple dimensions including depth based on the feature locations in the left camera image and the right camera image.

9. Apparatus for determining a feature location, comprising:

means for providing first and second spaced-apart camera images of the feature;

means for locating the feature in the first camera image using image analysis based on wavelet component values generated from wavelet transformations of the first camera image, and locating the feature in the second camera image using image analysis based on wavelet component values generated from wavelet transformations of the second camera image, wherein the feature is an eye of a person'"'"'s face; and

means for determining the feature location in multiple dimensions including depth based on the feature location in the first camera image and the feature location in the second camera image.

10. Apparatus for determining a feature location as defined in claim 9, wherein the wavelet transformations use Gabor wavelets.

11. A method for real-time determination of the location of a person'"'"'s eyes in three-dimensions for auto-stereoscopic imaging, comprising:

providing left and right spaced-apart camera images of a person'"'"'s face, the person'"'"'s face including a left eye and a right eye;

locating the left eye and the right eye in the left camera image using image analysis based on wavelet component values generated from wavelet transformations of the left camera image, and locating the left eye and the right eye in the right camera image using image analysis based on wavelet component values generated from wavelet transformations of the right camera image; and

determining the feature locations of the left eye and the right eye in three dimensions based on the left and right eye locations in the left camera image and the left and right eye locations in the right camera image.

12. A method for real-time determination of the location of a person'"'"'s eyes in three-dimensions for auto-stereoscopic imaging as defined in claim 11, wherein the wavelet transformations use Gabor wavelets.

13. A method for real-time determination of the location of a person'"'"'s eyes in three-dimensions for auto-stereoscopic imaging as defined in claim 12, wherein the image analysis comprises bunch graph matching.

14. Apparatus for real-time determination of the location of a person'"'"'s eyes in three-dimensions for auto-stereoscopic imaging, comprising:

means for providing left and right spaced-apart camera images of a person'"'"'s face, the person'"'"'s face including a left eye and a right eye;

means for locating the left eye and the right eye in the left camera image using image analysis based on wavelet component values generated from wavelet transformations of the left camera image, and locating the left eye and the right eye in the right camera image using image analysis based on wavelet component values generated from wavelet transformations of the right camera image; and

means for determining the feature locations of the left eye and the right eye in three dimensions based on the left and right eye locations in the left camera image and the left and right eye locations in the right camera image.

15. Apparatus for real-time determination of the location of a person'"'"'s eyes in three-dimensions for auto-stereoscopic imaging as defined in claim 14, wherein the wavelet transformations use Gabor wavelets.

16. Apparatus for real-time determination of the location of a person'"'"'s eyes in three-dimensions for auto-stereoscopic imaging as defined in claim 15, wherein the image analysis comprises bunch graph matching.