Systems and techniques for estimating eye pose
Inventors
Farmer, Daniel • Cohen, David • Stuart, Bradley Vincent
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12474775-B2
Publication Date
2025-11-18
Expiration Date
Abstract
An eye tracking system can include eye-tracking camera(s) configured to obtain images of the eye at different exposure times or different frame rates. For example, longer exposure images of the eye taken at a longer exposure time can show iris or pupil features, and shorter exposure, glint images can show peaks of glints reflected from the eye. The shorter exposure glint images may be taken at a higher frame rate than the longer exposure images for more accurate gaze prediction. The shorter exposure glint images can be analyzed to provide glint locations to subpixel accuracy. The longer exposure images can be analyzed for pupil center and/or center of rotation. The eye tracking system can predict gaze direction, which can be used for foveated rendering by a wearable display system. In some instances, the eye-tracking system may estimate the location of a partially or totally occluded glint.
Core Innovation
The invention describes a head-mounted system that captures images of a user’s eye using one or more cameras and a plurality of light sources that illuminate the eye to produce glints in the images. The system identifies a location in the image where a center of a pupil is shown and detects a set of one or more locations in the image where one or more glints are shown. The system determines whether a total quantity of detected glint locations is less than a particular value.
When the determination indicates that the total quantity of detected glint locations is less than the particular value, the system applies the identified pupil-center location and the detected glint locations to a probabilistic statistical model to estimate a set of one or more glint locations for the image. The estimated set of one or more glint locations is different than the detected set of one or more glint locations. The system then determines a pose of the eye of the user based at least in part on both the detected set of one or more glint locations and the estimated set of one or more glint locations.
The method aspect performs the same sequence using one or more processors of a head-mounted system. It receives an image of an eye captured by the one or more cameras, identifies a location where a center of a pupil is shown, and detects glint locations produced by the plurality of light sources. If the total quantity of detected glint locations is less than the particular value, it uses the probabilistic statistical model to estimate glint locations and determines a pose of the eye based on detected and estimated glint locations.
Claims Coverage
The partial content includes two independent claims, one for a head-mounted system and one for a corresponding method. Each independent claim centers on identifying a pupil-center location, detecting glint locations from multiple light sources, estimating additional glint locations with a probabilistic statistical model when the detected glint quantity is below a threshold, and determining eye pose.
Head-mounted system with pupil-center identification and glint-based pose estimation using a probabilistic statistical model when glint count is below threshold
A head-mounted system comprising one or more cameras capturing images of an eye and a plurality of light sources illuminating the eye to produce glints, where the processors receive an image, identify a location of a center of a pupil, detect glint locations, determine whether the total quantity of detected glint locations is less than a particular value, apply the identified pupil-center location and the detected glint locations to a probabilistic statistical model to estimate a different set of glint locations in response to the determination, and determine a pose of the eye based at least in part on the detected and estimated sets of glint locations.
Method for glint location estimation and pose determination using a probabilistic statistical model when glint count is below threshold
A method performed by one or more processors of a head-mounted system comprising receiving an image captured by one or more cameras, identifying a location in the image where a center of a pupil is shown, detecting glint locations produced by a plurality of light sources, determining whether the total quantity of detected glint locations is less than a particular value, and in response applying the identified pupil-center location and the detected glint locations to a probabilistic statistical model to estimate a different set of glint locations and determining a pose of the eye based at least in part on the detected and estimated sets of glint locations.
Across both independent claims, the core coverage is the same: detect pupil center and glint locations from head-mounted eye images illuminated by multiple light sources, branch when the detected glint quantity is less than a threshold, estimate additional glint locations using a probabilistic statistical model, and determine eye pose based on detected and estimated glint locations.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?