Gaile G Gordon

US Patent:

6445810, Sep 3, 2002

Filed:

Dec 1, 2000

Appl. No.:

09/726425

Inventors:

Trevor Darrell - San Francisco CA
Gaile Gordon - Palo Alto CA
Michael Harville - Palo Alto CA
John Woodfill - San Francisco CA
Harlyn Baker - Los Altos CA

Assignee:

Interval Research Corporation - Palo Alto CA

International Classification:

G06K 900

US Classification:

382115, 382118

Abstract:

Techniques from computer vision and computer graphics are combined to robustly track a target (e. g. , a user) and perform a function based upon the image and/or the identity attributed to the targets face. Three primary modules are used to track a users head: depth estimation, color segmentation, and pattern classification. The combination of these three techniques allows for robust performance despite unknown background, crowded conditions, and rapidly changing pose or expression of the user. Each of the modules can also provide an identity classification module with valuable information so that the identity of a user can be estimated. With an estimate of the position of a target in 3-D and the targets identity, applications such as individualized computer programs or graphics techniques to distort and/or morph the shape or apparent material properties of the users face can be performed. The system can track and respond to a users face in real-time using completely passive and non-invasive techniques.

US Patent:

6661918, Dec 9, 2003

Filed:

Dec 3, 1999

Appl. No.:

09/453450

Inventors:

Gaile Gordon - Palo Alto CA
Michael Harville - Palo Alto CA
John Woodfill - Palo Alto CA
Trevor Darrell - Boston MA

Assignee:

Interval Research Corporation - Palo Alto CA

International Classification:

G06K 934

US Classification:

382173, 382164

Abstract:

Segmentation of background and foreground objects in an image is based upon the joint use of both range and color data. Range-based data is largely independent of color image data, and hence not adversely affected by the limitations associated with color-based segmentation, such as shadows and similarly colored objects. Furthermore, color segmentation is complementary to range measurement in those cases where reliable range data cannot be obtained. These complementary sets of data are used to provide a multidimensional background estimation. The segmentation of a foreground object in a given frame of an image sequence is carried out by comparing the image frames with background statistics relating to range and normalized color, using the sets of statistics in a complementary manner.

US Patent:

7003134, Feb 21, 2006

Filed:

Mar 8, 2000

Appl. No.:

09/520964

Inventors:

Michele M. Covell - Los Altos Hills CA, US
Michael Hongmai Lin - Stanford CA, US
Ali Rahimi - Belmont CA, US
Michael Harville - Palo Alto CA, US
Trevor J. Darrell - San Francisco CA, US
John I. Woodfill - Palo Alto CA, US
Harlyn Baker - Los Altos CA, US
Gaile G. Gordon - Palo Alto CA, US

Assignee:

Vulcan Patents LLC - Seattle WA

International Classification:

G06K 9/00

US Classification:

382103, 382106, 382107

Abstract:

Dense range data obtained at real-time rates is employed to estimate the pose of an articulated figure. In one approach, the range data is used in combination with a model of connected patches. Each patch is the planar convex hull of two circles, and a recursive procedure is carried out to determine an estimate of pose which most closely correlates to the range data. In another aspect of the invention, the dense range data is used in conjunction with image intensity information to improve pose tracking performance. The range information is used to determine the shape of an object, rather than assume a generic model or estimate structure from motion. In this aspect of the invention, a depth constraint equation, which is a counterpart to the classic brightness change constraint equation, is employed. Both constraints are used to jointly solve for motion estimates.

US Patent:

7158656, Jan 2, 2007

Filed:

Aug 1, 2005

Appl. No.:

11/195039

Inventors:

Michele M. Covell - Los Altos Hills CA, US
Michael Hongmai Lin - Stanford CA, US
Ali Rahimi - Belmont CA, US
Michael Harville - Palo Alto CA, US
Trevor J. Darrell - San Francisco CA, US
John I. Woodfill - Palo Alto CA, US
Harlyn Baker - Los Altos CA, US
Gaile G. Gordon - Palo Alto CA, US

Assignee:

Vulcan Patents LLC - Seattle WA

International Classification:

G06K 9/00

US Classification:

382106, 382103, 382107, 348139

Abstract:

Dense range data obtained at real-time rates is employed to estimate the pose of an articulated figure. In one approach, the range data is used in combination with a model of connected patches. Each patch is the planar convex hull of two circles, and a recursive procedure is carried out to determine an estimate of pose which most closely correlates to the range data. In another aspect of the invention, the dense range data is used in conjunction with image intensity information to improve pose tracking performance. The range information is used to determine the shape of an object, rather than assume a generic model or estimate structure from motion. In this aspect of the invention, a depth constraint equation, which is a counterpart to the classic brightness change constraint equation, is employed. Both constraints are used to jointly solve for motion estimates.

US Patent:

7317830, Jan 8, 2008

Filed:

Nov 7, 2003

Appl. No.:

10/703393

Inventors:

Gaile Gordon - Palo Alto CA, US
Trevor Darrell - Boston MA, US
Michael Harville - Palo Alto CA, US
John Woodfill - San Francisco CA, US

Assignee:

Vulcan Patents LLC - Seattle CA

International Classification:

G06K 9/34

US Classification:

382173

Abstract:

Segmentation of background and foreground objects in an image is based upon the joint use of range and color data. Range-based data is largely independent of color image data, and hence not adversely affected by the limitations associated with color-based segmentation, such as shadows and similarly colored objects. Furthermore, color segmentation is complementary to range measurement in those cases where reliable range data cannot be obtained. These complementary sets of data are used to provide a multidimensional background estimation. The segmentation of a foreground object in a given frame of an image sequence is carried out by comparing the image frames with background statistics relating to range and normalized color, using the sets of statistics in a complementary manner. A background model is determined by estimating using a multidimensional histogram, recording pixel values, configuring the pixel values into a cluster, and selecting a largest cluster as representing the background model.

US Patent:

7664315, Feb 16, 2010

Filed:

Oct 31, 2005

Appl. No.:

11/264760

Inventors:

John Iselin Woodfill - Palo Alto CA, US
Ronald John Buck - Fremont CA, US
Gaile Gibson Gordon - Palo Alto CA, US
David Walter Jurasek - Banks OR, US
Terrence Lee Brown - Portland OR, US

Assignee:

Tyzx, Inc. - Menlo Park CA

International Classification:

G06K 9/00
G06K 9/36

US Classification:

382154, 382285, 382303, 345419, 356 12, 348 42, 359462

Abstract:

An integrated image processor implemented on a substrate is disclosed. An input interface is configured to receive pixel data from two or more images. A pixel handling processor disposed on the substrate is configured to convert the pixel data into depth and intensity pixel data. In some embodiments, a foreground detector processor disposed on the substrate is configured to classify pixels as background or not background. In some embodiments, a projection generator disposed on the substrate is configured to generate a projection in space of the depth and intensity pixel data.

US Patent:

7970177, Jun 28, 2011

Filed:

Mar 22, 2007

Appl. No.:

11/728202

Inventors:

Pierre St. Hilaire - Belmont CA, US
Gaile Gibson Gordon - Palo Alto CA, US
John Iselin Woodfill - Palo Alto CA, US
Ronald J. Buck - Fremont CA, US
Steve Clohset - San Francisco CA, US

Assignee:

Tyzx, Inc. - Menlo Park CA

International Classification:

G06K 9/00

US Classification:

382106, 382154

Abstract:

A system for distance calculation is disclosed. The system includes an illuminator unit, one or more camera units, and a distance processor. The illuminator unit illuminates a scene in a target area using a textured pattern creator and wherein the textured pattern creator includes a diffractive optical element. The one or more camera units captures two or more images of the target area from two or more physical locations. A textured pattern illumination is visible in each of the two or more images of the target area. The images are used to calculate distances to one or more points in the scene in the target area.

US Patent:

8238611, Aug 7, 2012

Filed:

May 20, 2011

Appl. No.:

13/112247

Inventors:

Pierre St. Hilaire - Belmont CA, US
Gaile Gibson Gordon - Palo Alto CA, US
John Iselin Woodfill - Palo Alto CA, US
Ronald John Buck - Fremont CA, US
Steve Clohset - San Francisco CA, US

Assignee:

Tyzx, Inc. - Menlo Park CA

International Classification:

G06K 9/00

US Classification:

382106, 382154

Abstract:

A system for distance calculation is disclosed. The system includes an illuminator unit, one or more camera units, and a distance processor. The illuminator unit illuminates a scene in a target area using a textured pattern creator and wherein the textured pattern creator includes a diffractive optical element. The one or more camera units captures two or more images of the target area from two or more physical locations. A textured pattern illumination is visible in each of the two or more images of the target area. The images are used to calculate distances to one or more points in the scene in the target area.