Calibration for eye tracking systems

Patent metadata

Field	Value
Publication number	US-9936195-B2
Application number	US-201414534333-A
Country	US
Kind code	B2
Filing date	Nov 6, 2014
Priority date	Nov 6, 2014
Publication date	Apr 3, 2018
Grant date	Apr 3, 2018

Abstract

Generally, this disclosure provides systems, devices, methods and computer readable media for calibration of an eye tracking system. In some embodiments, the method may include analyzing a video stream received from a scene facing camera to detect moving objects and estimate angular locations of the moving objects. The method may also include receiving images from an eye tracking camera and estimating gaze angles of a user's eye, based on the images. The method may further include computing, for each of the moving objects, a first distance measure between the object angular locations and the gaze angles; accepting or rejecting each of the moving objects for use in calibration based on a comparison of the first distance measure to a threshold; and estimating an eye tracking calibration angle based on a minimization of a second distance measure computed between the angular locations of the accepted moving objects and the gaze angles.

First claim

What is claimed is:

1. An eye tracking calibration system comprising:
an eye tracking camera to track eye movement of a user in communication with a gaze estimation circuitry;
a scene facing camera in communication with a scene analysis circuitry;
an inertial sensor in communication with said scene analysis circuitry;
said scene analysis circuitry detecting moving objects and estimating angular locations of said moving objects over a period of time, wherein said moving objects include two or more objects in a field of view surrounding a user;
said gaze estimation circuitry receiving images from said eye tracking camera and estimating gaze angles of a user's eye, based on said images, over said period of time;
an object trajectory matching circuitry computing, for each of said moving objects, a first distance measure between said object angular locations and said gaze angles, and further to decide on acceptance of said each moving object for use in calibration based on a comparison of said first distance measure to a distance measure threshold; and
a calibration circuitry estimating an eye tracking calibration angle based on a minimization of a second distance measure, said second distance measure computed between said angular locations of said accepted moving objects and said gaze angles.

2. The system of claim 1 , wherein said scene analysis circuitry detects said moving objects based on template matching, optical flow tracking, background segmentation, Scale Invariant Feature Transform (SIFT) matching, particle filtering and/or Positive-Negative tracking.

3. The system of claim 1 , wherein said scene analysis circuitry rejects said moving objects based on a visual size of said moving object exceeding a size threshold.

4. The system of claim 1 , wherein said scene analysis circuitry rejects said moving objects based on a visual speed of said moving object exceeding a speed threshold.

5. The system of claim 1 , wherein said scene analysis circuitry rejects said moving objects based on a determination that the extremities of said gaze angle associated with said moving object fail to exceed a range of motion threshold.

6. The system of claim 1 , wherein said minimization is based on a Newton-Gauss algorithm or a Levenberg-Marquardt algorithm.

7. The system of claim 1 , further comprising a depth measurement device estimating the distance between said moving object and said scene facing camera for conversion of locations of said moving objects from a world coordinate system to an eye coordinate system.

8. The system of claim 1 , wherein said object trajectory matching circuitry further resamples said estimated object angular locations and said estimated gaze angles to a common time coordinate system.

9. A method for eye tracking calibration comprising:
providing an eye tracking calibration system in communication with an eye tracking camera to track eye movement of a user, and a scene facing camera, and an inertial sensor in communication, wherein:
said eye tracking camera is in communication with a gaze estimation circuitry;
said scene facing camera is in communication with a scene analysis circuitry;
said inertial sensor is in communication with said scene analysis circuitry;
said method further comprising:
receiving a video stream from said scene facing camera;
analyzing said video stream to detect moving objects and estimating angular locations of said moving objects over a period of time, wherein said moving objects include two or more objects in a field of view surrounding a user;
receiving images from said eye tracking camera and estimating gaze angles of a user's eye, based on said images, over said period of time;
computing, for each of said moving objects, a first distance measure between said object angular locations and said gaze angles;
deciding on acceptance of said each moving object for use in calibration based on a comparison of said first distance measure to a distance measure threshold; and
estimating an eye tracking calibration angle based on a minimization of a second distance measure, said second distance measure computed between said angular locations of said accepted moving objects and said gaze angles.

10. The method of claim 9 , further comprising detecting said moving objects based on template matching, optical flow tracking, background segmentation, Scale Invariant Feature Transform (SIFT) matching, particle filtering and/or Positive-Negative tracking.

11. The method of claim 9 , further comprising rejecting said moving objects based on a visual size of said moving object exceeding a size threshold.

12. The method of claim 9 , further comprising rejecting said moving objects based on a visual speed of said moving object exceeding a speed threshold.

13. The method of claim 9 , further comprising rejecting said moving objects based on a determination that the extremities of said gaze angle associated with said moving object fail to exceed a range of motion threshold.

14. The method of claim 9 , further comprising tracking motion of said scene facing camera and rejecting said moving objects based on a correlation of said object motion with said scene facing camera motion.

15. The method of claim 9 , wherein said minimization is based on a Newton-Gauss algorithm or a Levenberg-Marquardt algorithm.

16. The method of claim 9 , further comprising estimating the distance between said moving object and said scene facing camera for conversion of locations of said moving objects from a world coordinate system to an eye coordinate system.

17. The method of claim 9 , further comprising resampling said estimated object angular locations and said estimated gaze angles to a common time coordinate system.

18. At least one non-transitory computer-readable storage medium disposed within a an eye tracking calibration system and having instructions stored thereon, said eye tracking calibration system further comprising an eye tracking camera in communication with a gaze estimation circuitry, a scene facing camera in communication with a scene analysis circuitry, and an inertial sensor in communication with said scene analysis circuitry, wherein when said instructions are executed by a processor result in the following operations for eye tracking calibration, said operations comprising:
receiving a video stream from said scene facing camera;
detecting moving objects and estimating angular locations of said moving objects over a period of time, wherein said moving objects include two or more objects in a field of view surrounding a user;
receiving images from an eye tracking camera and estimating gaze angles of a user's eye, based on said images, over said period of time;
computing, for each of said moving objects, a first distance measure between said object angular locations and said gaze angles;
deciding on acceptance of said each moving object for use in calibration based on a comparison of said first distance measure to a distance measure threshold; and
estimating an eye tracking calibration angle based on a minimization of a second distance measure, said second distance measure computed between said angular locations of said accepted moving objects and said gaze angles.

19. The non-transitory computer-readable storage medium of claim 18 , further comprising the operation of detecting said moving objects based on template matching, optical flow tracking, background segmentation, Scale Invariant Feature Transform (SIFT) matching, particle filtering and/or Positive-Negative tracking.

20. Th

Assignees

• Intel Corp

Inventors

• Horesh Nizan

Classifications

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title

• G06F3/0304

  Detection arrangements using opto-electronic means (constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042) · CPC title

• H04N7/183

  for receiving images from a single remote source · CPC title

• H04N17/002 Primary

  for television cameras · CPC title