Dual-Exposure Eye Tracking for Accurate Gaze Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing VR, AR, and MR technologies face challenges in accurately tracking eye movements due to glint saturation in longer exposure images, leading to uncertainties in gaze direction estimation, which can cause eye strain and discomfort.
Innovation Solution
A dual-exposure time eye tracking system that utilizes shorter exposure glint images for precise glint location detection and longer exposure images for pupil center analysis, processed separately by different processors, to enhance gaze prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If longer exposure images are used for eye tracking, then more eye features (iris, pupil) are visible, but glint saturation occurs leading to inaccurate gaze direction estimation
Solution Approach 1:
The patent segments the eye tracking task into two separate processing paths: one for detecting glints using short exposure images, and another for detecting pupil/iris features using long exposure images. This segmentation allows each path to use optimal exposure settings for its specific detection goal, preventing glint saturation while ensuring feature visibility.
Solution Approach 2:
The patent introduces an intermediary processing step where glint locations are detected from short exposure images and then used to mask or guide the analysis of long exposure images. This intermediary approach prevents saturated glint regions from corrupting the gaze direction calculation while still utilizing the rich feature information from long exposure images.
2Measurement precision
If shorter exposure images are used for glint detection, then glint locations are accurate, but pupil and iris features are not visible
Solution Approach 1:
The patent merges the advantages of both short and long exposure images by combining their respective detection results. Short exposure images provide accurate glint locations, while long exposure images provide pupil and iris feature information. The system combines these complementary data sources to achieve both accurate glint detection and complete eye feature analysis.
Solution Approach 2:
The patent adds a temporal dimension to the imaging process by capturing images at multiple different exposure times. Instead of relying on a single exposure setting, the system captures short exposure images for glint detection and long exposure images for feature detection, utilizing the time dimension to overcome the limitations of each individual exposure setting.
3Device complexity
If single exposure time imaging is used, then system complexity is low, but gaze prediction accuracy is insufficient
Solution Approach 1:
The patent implements periodic action by alternating between short and long exposure image captures in a structured sequence. The system periodically switches exposure settings to capture the complementary information needed for accurate gaze prediction, maintaining a rhythm that balances computational load with measurement accuracy.
Solution Approach 2:
The patent changes the exposure time parameter dynamically based on the detection goal. By adjusting the exposure time parameter between short and long settings, the system optimizes image quality for different detection tasks (glint vs. feature detection) without requiring fundamentally different hardware systems.
4Loss of time
If high frame rate imaging is used for accurate gaze tracking, then rendering latency is reduced, but energy consumption increases
Solution Approach 1:
The patent applies partial action by using different frame rates for different image types. Instead of capturing all images at maximum frame rate, the system uses high frame rates only for short exposure glint images where temporal accuracy is critical, while using lower frame rates for long exposure feature images, thereby reducing overall energy consumption while maintaining gaze tracking accuracy.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Accurately predicts future gaze direction with subpixel precision, reducing rendering latency and enhancing user comfort by minimizing eye strain and accommodation conflicts.
Implementation Method 1
images of the eye taken at shorter exposure times (sometimes referred to as glint images) can show peaks of glints reflected from the cornea
Data Source
AI summary
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.