CALIBRATION OF EYE TRACKING SYSTEM

• US 20140055591A1
• Filed: 08/24/2012
• Published: 02/27/2014
• Est. Priority Date: 08/24/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Katz, Sagi
• Granted Patent: US 9,164,580 B2
• Time in Patent Office: Days
• US Class Current: 348/78
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 3/013 Eye tracking input arrangements G06F3/015 takes precedence

Abstract

Embodiments are disclosed that relate to calibrating an eye tracking system for a computing device. For example, one disclosed embodiment provides, in a computing device comprising a gaze estimation system, a method of calibrating the gaze estimation system. The method includes receiving a request to log a user onto the computing device, outputting a passcode entry display image to a display device, receiving image data from one or more eye tracking cameras, and from the image data, determining a gaze scanpath representing a path of a user'"'"'s gaze on the passcode entry display image. The method further includes comparing the gaze scanpath to a stored scanpath for the user, and calibrating the gaze estimation system based upon a result of comparing the gaze scanpath to the stored scanpath for the user.

Claims

1. In a computing device comprising a gaze estimation system including one or more eye tracking cameras and one or more eye glint light sources, a method of calibrating the gaze estimation system, the method comprising:

receiving a request to log a user onto the computing device;

outputting a passcode entry display image to a display device;

receiving image data from the one or more eye tracking cameras;

from the image data, determining a gaze scanpath representing a detected path of a user'"'"'s gaze on the passcode entry display image;

comparing the gaze scanpath to a stored scanpath for the user; and

calibrating the gaze estimation system based upon a result of comparing the gaze scanpath to the stored scanpath for the user.

2. The method of claim 1, wherein calibrating the gaze estimation system comprises determining a determined offset between the gaze scanpath and the stored scanpath.

3. The computing device of claim 2, further comprising comparing the determined offset with a stored offset, and log on the user only if the determined offset matches the stored offset.

4. The method of claim 1, further comprising adjusting the gaze scanpath to form an adjusted gaze scanpath based upon calibrating the gaze scanpath, and if the adjusted gaze scanpath matches the stored scanpath, then logging on the user.

5. The method of claim 1, further comprising not calibrating the gaze estimation system if the gaze scanpath meets one or more disqualifying criteria.

6. The method of claim 1, wherein calibrating the gaze scanpath to the stored scanpath comprises minimizing an error function that compares the gaze scanpath to the stored scanpath.

7. The method of claim 1, wherein the outputting the passcode entry display image comprises outputting a picture.

8. The method of claim 1, wherein outputting the passcode entry display image comprises outputting the passcode entry display image to a near-eye display.

9. A computing device comprising:

a logic subsystem; and

a data-holding subsystem comprising instructions stored thereon that are executable by the logic subsystem to;

receive a request to log a user onto the computing device;

output a passcode entry display image to a display device;

receive image data from a gaze estimation system comprising one or more eye tracking cameras;

from the image data, determine a gaze scanpath representing a path of a user'"'"'s gaze on the passcode entry display image;

compare the gaze scanpath to a stored scanpath for the user;

calibrate the gaze estimation system based upon a result of comparing the gaze scanpath to the stored scanpath for the user;

adjust the gaze scanpath to form an adjusted gaze scanpath based upon calibrating the gaze scanpath; and

if the adjusted gaze scanpath matches the stored scanpath, then log on the user.

10. The computing device of claim 9, wherein the computing device comprises the gaze estimation system.

11. The computing device of claim 9, wherein the computing device is a wearable computing device comprising a near-eye display.

12. The computing device of claim 9, wherein the instructions are executable to calibrate the gaze estimation system by determining a determined offset between the gaze scanpath and the stored scanpath.

13. The computing device of claim 12, wherein the instructions are further executable to compare the determined offset to a stored offset, and to log in the user only if the determined offset matches the stored offset and the adjusted scanpath matches the stored scanpath.

14. The computing device of claim 13, wherein the instructions are executable to determine the determined offset by minimizing an error function that compares the gaze scanpath to the stored scanpath for the user.

15. The computing device of claim 9, wherein the instructions are further executable to not calibrate the gaze estimation system if the gaze scanpath meets one or more disqualifying criteria.

16. A computing device, comprising:

a logic subsystem; and

a data-holding subsystem comprising instructions stored thereon that are executable by the logic subsystem to;

receive a request to log a user onto the computing device;

output a passcode entry picture to a display device;

receive image data from a gaze estimation system comprising one or more eye tracking cameras;

from the image data, determine a gaze scanpath representing a path of a user'"'"'s gaze on the passcode entry display image;

if the gaze scanpath meets one or more disqualifying criteria, then rejecting the gaze scanpath and not logging on the user;

if the gaze scanpath does not meet any of the one or more disqualifying criteria, then comparing the gaze scanpath to a stored scanpath for the user;

calibrating the gaze estimation system based upon a result of comparing the gaze scanpath to the stored scanpath for the user;

adjusting the gaze scanpath to form an adjusted gaze scanpath based upon calibrating the gaze scanpath; and

if the adjusted gaze scanpath matches the stored scanpath, then logging on the user.

17. The computing device of claim 16, wherein the computing device is a wearable computing device comprising a head-mounted display.

18. The computing device of claim 16, wherein the instructions are executable to calibrate the gaze estimation system by determining a determined offset between the gaze scanpath and the stored scanpath.

19. The computing device of claim 18, wherein the instructions are further executable to compare the determined offset to a stored offset, and to log in the user only if the determined offset matches the stored offset and the adjusted scanpath matches the stored scanpath.

20. The computing device of claim 18, wherein the instructions are executable to determine the determined offset by minimizing an error function that compares the gaze scanpath to the stored scanpath for the user.