IP Library › Granted Patent US 10,664,049
Granted Patent B2
US 10,664,049 · App. 15/809,849 · Granted May 26, 2020

Systems and methods for gaze tracking

Inventors: Joohwan Kim (Berkeley, CA); Ward Lopes (Redwood City, CA); David Patrick Luebke (Charlottesville, VA); Chengyuan Lin (West Lafayette, IN)
Assignee: NVIDIA Corporation
G06F3/013A61B3/113G02B27/0093G02B27/0103G02B27/0172G06F3/01G06K9/00604G02B2027/0105G02B2027/0174G02B2027/0187
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,664,049
App. No.
15/809,849
Granted
May 26, 2020
Kind
B2
Abstract

A method, computer readable medium, and system are disclosed for gaze tracking. The method includes the steps of receiving reflected light rays at an optical sensor, where all of the reflected light rays converge towards a rotational center of an eye and generating pattern data based on intersections of the reflected light rays at a surface of the optical sensor. A processor computes an estimated gaze direction of the eye based on the pattern data.

Claims (240)

1. A gaze tracking system, comprising:

an optical sensor configured to:

receive reflected light rays produced by light rays that converge toward a rotational center of an eye and are reflected by one or more optical components of the eye toward the optical sensor, and

generate pattern data based on intersections of the reflected light rays at a surface of the optical sensor,

wherein the optical sensor is a quadrant photo detector and the pattern data includes an illumination intensity value corresponding to each quadrant of the quadrant photo detector; and

a processor configured to compute an estimated gaze direction of the eye based on the pattern data by calculating a displacement based on the illumination intensity value for each quadrant.

2. The gaze tracking system of claim 1 , wherein at least a portion of the reflected light rays reflect off a retina of the eye.

3. The gaze tracking system of claim 1 , wherein at least a portion of the reflected light rays reflect off a cornea or a crystalline lens of the eye.

4. The gaze tracking system of claim 1 , wherein computing the estimated gaze direction comprises:

computing a horizontal displacement based on the illumination intensity values according to the following equation:

[

(

Q

⁢

⁢

2

+

Q

⁢

⁢

3

)

-

(

Q

⁢

⁢

1

+

Q

⁢

⁢

4

)

]

[

(

Q

⁢

⁢

2

+

Q

⁢

⁢

3

)

+

(

Q

⁢

⁢

1

+

Q

⁢

⁢

4

)

]

;

computing a vertical displacement based on the illumination intensity values according to the following equation:

[

(

Q

⁢

⁢

1

+

Q

⁢

⁢

2

)

-

(

Q

⁢

⁢

3

+

Q

⁢

⁢

4

)

]

[

(

Q

⁢

⁢

1

+

Q

⁢

⁢

2

)

+

(

Q

⁢

⁢

3

+

Q

⁢

⁢

4

)

]

;

and

mapping the horizontal displacement and the vertical displacement to a position within a display, wherein Q 1 is an illumination intensity value for a first quadrant of the quadrant photo detector, Q 2 is an illumination intensity value for a second quadrant of the quadrant photo detector, Q 3 is an illumination intensity value for a third quadrant of the quadrant photo detector, and Q 4 is an illumination intensity value for a fourth quadrant of the quadrant photo detector.

5. The gaze tracking system of claim 1 , further comprising an adjustable mirror configured to direct the reflected light rays along a path to reach the optical sensor, wherein computing the estimated gaze direction comprises:

adjusting a steering angle of the adjustable mirror relative to the optical detector to center the pattern data at the surface of the optical detector; and

computing a position within a display based on the steering angle.

6. The gaze tracking system of claim 1 , further comprising an optical element configured to direct the reflected light rays from the eye along a path to reach the optical sensor.

7. The gaze tracking system of claim 6 , wherein the optical element is a holographic optical element.

8. The gaze tracking system of claim 6 , wherein the optical element is a beam splitter.

9. The gaze tracking system of claim 1 , wherein the reflected light rays include retro-reflected light rays.

10. The gaze tracking system of claim 1 , further comprising measuring a gaze direction error produced by a misalignment between an original orientation between the eye and the optical sensor and a current orientation between the eye and the optical sensor, wherein the processor is further configured to compute the estimated gaze direction of the eye based on the gaze direction error.

11. A computer-implemented method, comprising:

receiving reflected light rays at an optical sensor, wherein light rays produced by a light source converge towards a rotational center of an eye and are reflected by one or more optical components of the eye toward the optical sensor as the reflected light rays; and

generating pattern data based on intersections of the reflected light rays at a surface of the optical sensor,

wherein the optical sensor is a quadrant photo detector and the pattern data includes an illumination intensity value corresponding to each quadrant of the quadrant photo detector; and

computing, by a processor, an estimated gaze direction of the eye based on the pattern data by calculating a displacement based on the illumination intensity value for each quadrant.

12. The computer-implemented method of claim 11 , wherein at least a portion of the reflected light rays reflect off a retina of the eye.

13. The computer-implemented method of claim 11 , wherein at least a portion of the reflected light rays reflect off a cornea or a crystalline lens of the eye.

14. The computer-implemented method of claim 11 , wherein computing the estimated gaze direction comprises:

computing a horizontal displacement based on the illumination intensity values according to the following equation:

[

(

Q

⁢

⁢

2

+

Q

⁢

⁢

3

)

-

(

Q

⁢

⁢

1

+

Q

⁢

⁢

4

)

]

[

(

Q

⁢

⁢

2

+

Q

⁢

⁢

3

)

+

(

Q

⁢

⁢

1

+

Q

⁢

⁢

4

)

]

;

computing a vertical displacement based on the illumination intensity values according to the following equation:

[

(

Q

⁢

⁢

1

+

Q

⁢

⁢

2

)

-

(

Q

⁢

⁢

3

+

Q

⁢

⁢

4

)

]

[

(

Q

⁢

⁢

1

+

Q

⁢

⁢

2

)

+

(

Q

⁢

⁢

3

+

Q

⁢

⁢

4

)

]

;

and

mapping the horizontal displacement and the vertical displacement to a position within a display, wherein Q 1 is an illumination intensity value for a first quadrant of the quadrant photo detector, Q 2 is an illumination intensity value for a second quadrant of the quadrant photo detector, Q 3 is an illumination intensity value for a third quadrant of the quadrant photo detector, and Q 4 is an illumination intensity value for a fourth quadrant of the quadrant photo detector.

15. A non-transitory, computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform steps comprising:

generating pattern data based on intersections of reflected light rays at a surface of an optical sensor, wherein light rays produced by a light source converge towards a rotational center of an eye and are reflected by one or more optical components of the eye toward the optical sensor as the reflected light rays, wherein the optical sensor is a quadrant photo detector and the pattern data includes an illumination intensity value corresponding to each quadrant of the quadrant photo detector; and

computing an estimated gaze direction of the eye based on the pattern data by calculating a displacement based on the illumination intensity value for each quadrant.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 15, 2017
From: KIM, JOOHWAN; LOPES, WARD; LUEBKE, DAVID PATRICK; LIN, CHENGYUAN
To: NVIDIA CORPORATION
Reel/Frame 044135/0338 →
Continuity (2)
Provisional Application 62432454 · Dec 9, 2016
Related Publication 20180164880A1 · Jun 14, 2018
Cited By (2)
US 12,329,514 US 12,664,185