Cornea Model Update via Multi-Depth Stimuli for Eye Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Single-camera eye tracking systems face challenges in determining an accurate cornea model, leading to inaccuracies in eye tracking performance, especially when users move their head or observe objects at different depths, as they rely on less accurate cornea models and compensation methods.
Innovation Solution
A method and system that update the cornea model by displaying stimuli at different depths, using sensor data from an eye tracking sensor to adjust and refine the cornea model parameters, allowing for more accurate gaze estimation and depth measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single-camera eye tracker is employed, then device complexity is reduced, but cornea model accuracy deteriorates
Solution Approach 1:
The system changes the depth parameter of displayed stimuli to collect sensor data at multiple depths. By displaying stimuli at different depths and analyzing how the eye adjusts focus and position, the system extracts multiple parameters (pupil center position, corneal reflection positions at different depths) that are then used to compute an accurate cornea model even with a single camera.
2Ease of operation
If calibration is performed assuming fixed head position, then ease of operation is improved, but reliability deteriorates when head moves
Solution Approach 1:
The system transitions from static calibration (fixed head position assumption) to dynamic calibration. By displaying stimuli at multiple depths and collecting sensor data during natural head movements and focus adjustments, the system captures dynamic eye behavior. The cornea model is then updated based on this dynamic data, making the system reliable even when the user moves their head or changes viewing distance.
3Device complexity
If a less accurate cornea model is used, then device complexity is reduced, but gaze estimation accuracy deteriorates
Solution Approach 1:
The system adds the depth dimension to the calibration process by displaying stimuli at multiple depths rather than a single plane. This provides additional information about the eye's optical properties at different focal distances. The cornea model is updated using this multi-depth information, enabling accurate gaze estimation in 3D space rather than just on a 2D display plane.
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
This approach improves eye tracking accuracy by refining the cornea model, enabling better gaze estimation and depth measurements, even in scenarios where users move their head or observe objects at varying distances, enhancing performance in virtual and augmented reality applications.
Implementation Method 1
PCCR-based eye tracking employs the position of the pupil center and the position of glints (reflections of illuminators at the cornea) to compute a gaze direction of the eye or a gaze point at a display
Data Source
AI summary
A method of updating a cornea model for a cornea of an eye is disclosed, as well as a corresponding system and storage medium. The method comprises controlling a display to display a stimulus at a first depth, wherein the display is capable of displaying objects at different depths, receiving first sensor data obtained by an eye tracking sensor while the stimulus is displayed at the first depth by the display, controlling the display to display a stimulus at a second depth, wherein the second depth is different than the first depth, receiving second sensor data obtained by the eye tracking sensor while the stimulus is displayed at the second depth by the display, and updating the cornea model based on the first sensor data and the second sensor data.