Systems and methods for tracking the eye
First Claim
Patent Images
1. A method for tracking an eye in eye movement space, the method comprising:
- providing a means for illuminating the eye;
providing a means comprising multiple sensors for acquiring stereo images of the eye from different spatial perspectives;
acquiring stereo images of the eye using multiple sensors;
isolating internal features of the eye from the stereo images acquired from the multiple sensors;
isolating specular reflection points on a corneal surface of the eye, the specular reflection points resulting from reflections of light emitted from a plurality of light sources sequentially used to illuminate the eye;
computing a center and radius of the spherical corneal surface using the specular reflection points;
calculating three-dimensional coordinates of the isolated internal features within the eye by performing ray tracing;
matching features across stereo images that are acquired by separate sensors, wherein the matching process makes use of the distribution of the features about apparent pupil elements common to both imageswherein performing ray tracing comprises computing feature locations from intersections of stereo-matched rays, wherein the stereo-matched rays have been derived using a refractive computational process; and
determining an eye gaze direction relative to the isolated internal features.
1 Assignment
0 Petitions
Accused Products
Abstract
Disclosed are systems and methods for tracking the eye. In one embodiment, a method for tracking the eye includes acquiring stereo images of the eye using multiple sensors, isolating internal features of the eye in the stereo images acquired from the multiple sensors, and determining an eye gaze direction relative to the isolated internal features.
69 Citations
19 Claims
-
1. A method for tracking an eye in eye movement space, the method comprising:
-
providing a means for illuminating the eye; providing a means comprising multiple sensors for acquiring stereo images of the eye from different spatial perspectives; acquiring stereo images of the eye using multiple sensors; isolating internal features of the eye from the stereo images acquired from the multiple sensors; isolating specular reflection points on a corneal surface of the eye, the specular reflection points resulting from reflections of light emitted from a plurality of light sources sequentially used to illuminate the eye; computing a center and radius of the spherical corneal surface using the specular reflection points; calculating three-dimensional coordinates of the isolated internal features within the eye by performing ray tracing; matching features across stereo images that are acquired by separate sensors, wherein the matching process makes use of the distribution of the features about apparent pupil elements common to both images wherein performing ray tracing comprises computing feature locations from intersections of stereo-matched rays, wherein the stereo-matched rays have been derived using a refractive computational process; and determining an eye gaze direction relative to the isolated internal features. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A system for tracking an eye movement space, the system comprising:
-
means for illuminating the eye; means for acquiring stereo images of the eye from different spatial perspectives; means for isolating specular reflections on a corneal surface of the eye in the stereo images; means for isolating internal features of the eye in the stereo images; and means for determining an eye gaze direction relative to the isolated internal features, wherein the means for determining an eye gaze direction comprise a ray tracer that calculates a center and radius of the spherical corneal surface using the specular reflection points, and the coordinates of the isolated internal features of the eye relative to a computed corneal surface using ray-tracing techniques, and a stereo reconstructor that matches isolated internal features across stereo images acquired by separate sensors using a best fit feature vector approach; and wherein the ray tracer computes feature locations from intersections of stereo-matched rays, wherein the stereo-matched rays have been derived using a refractive computational process. - View Dependent Claims (9, 10, 11, 12, 13)
-
-
14. An eye gaze tracking system, comprising:
-
a light source that is configured to illuminate a user'"'"'s eye; light sensors that are configured to be positioned at different locations relative to the eye and capture stereo images of the eye from different spatial perspectives; an opto-electronic device that is configured to receive stereo images from the light sensors and isolate specular reflection points on a corneal surface of the eye that correspond to reflections of light emitted from the light source; an image processor that is configured to isolate internal features of the eye, compute a center and radius of the spherical corneal surface using the specular reflection points, and calculate three-dimensional coordinates of the isolated internal features within the eye by performing ray tracing; a stereo reconstructor that is configured to match internal features isolated by the image processor across stereo images acquired by separate sensors, wherein the matching process makes use of the distribution of the features about apparent pupil elements common to both images; and a ray tracer that is configured to calculate the coordinates of the isolated internal features of the eye relative to a computed corneal surface from intersections of stereo-matched rays, wherein the stereo-matched rays have been derived using a refractive computational process. - View Dependent Claims (15, 16, 17, 18, 19)
-
Specification