Gaze Tracking Pupil Center Mapping Radial Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Gaze tracking systems, particularly in head-mounted devices, face challenges in accuracy and precision for large gaze angles due to noise in detecting corneal reflections, and existing solutions often require additional equipment that increases cost and complexity.
Innovation Solution
A method that employs a calibrated mapping of the pupil center to estimate gaze points, using a combination of image analysis and stimulus points for calibration, which improves gaze tracking performance by switching between different tracking methods based on gaze angle, reducing the need for additional cameras and illuminators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If additional cameras and illuminators are added to improve gaze tracking for large gaze angles, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system dynamically switches between PCCR-based gaze tracking and pupil center mapping-based gaze tracking depending on the detected gaze angle. For small gaze angles, PCCR is used; for large gaze angles, pupil center mapping is used. This dynamic adaptation allows the system to maintain high measurement precision across all gaze angles without requiring additional hardware for every possible condition.
Solution Approach 2:
The system changes the operational parameters by switching between two different gaze tracking methodologies based on the gaze angle parameter. When the gaze angle exceeds a threshold, the system transitions from PCCR-based tracking to pupil center mapping-based tracking, effectively adapting to different operational conditions without hardware changes.
2Measurement precision
If additional cameras and illuminators are added to improve gaze tracking for large gaze angles, then measurement precision is improved, but cost increases
Solution Approach 1:
The existing camera and illuminator in the head-mounted device are made multi-functional by utilizing them for both PCCR-based gaze tracking and pupil center mapping-based gaze tracking. The same hardware components serve multiple purposes depending on the operational mode, eliminating the need for additional dedicated equipment for large gaze angle tracking.
Solution Approach 2:
The system uses its existing resources (camera and illuminator) to solve the problem of large gaze angle tracking. By implementing pupil center mapping algorithms in the processing circuitry, the system leverages its own existing components to provide enhanced functionality without requiring external additions.
3Measurement precision
If additional cameras and illuminators are added to improve gaze tracking for large gaze angles, then measurement precision is improved, but the space available for other components is reduced
Solution Approach 1:
The existing camera and illuminator are made multi-functional by utilizing them for both PCCR-based gaze tracking and pupil center mapping-based gaze tracking. The same hardware components serve multiple purposes depending on the operational mode, eliminating the need for additional dedicated equipment for large gaze angle tracking.
Data Source
Figure 1~2
Figure 3~4
Figure 5~7
AI summary
Images of an eye (100) are captured by a camera (302). For each of the images, gaze data is obtained (402) and a position of a pupil center (103) is estimated (403) in the image. The gaze data indicates a gaze point (111) and/or gaze direction (107) of the eye (100) when the image was captured. A mapping (510, 520, 530) is calibrated (404) using the obtained gaze data and the estimated positions of the pupil center. The mapping maps positions of the pupil center in images (501) captured by the camera to gaze points (511, 521) at a surface (512, 522), or to gaze directions (531). A further image of the eye is captured by the camera. A position of the pupil center is estimated (406) in the further image. Gaze tracking is performed (407) using the calibrated mapping and the estimated position of the pupil center in the further image, wherein the gaze tracking is performed by applying a radial correction to the mapping, wherein the radial correction involves use of a correction function, wherein a size of the correction function depends on a gaze angle (703) of the eye. These steps may for example be performed at a HMD (1501).