Gaze Tracking Offset Model Using Pupil Size Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Gaze tracking systems face inaccuracies due to the movement of the pupil relative to the cornea, especially in varying light conditions, as the pupil does not open and close concentrically, affecting the estimated eye direction and angular offset to the gaze direction.
Innovation Solution
A computer-implemented method and system that determine limbus center, pupil center, and radius values at a sampling rate to form an offset model describing the estimated offset between the limbus center and pupil center as a function of pupil size, using linear regression to estimate constant values and update the model dynamically.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If gaze tracking is performed by measuring pupil location relative to cornea, then gaze direction can be estimated, but accuracy deteriorates when pupil expands and contracts in varying light conditions
Solution Approach 1:
The system dynamically adjusts the reference point for gaze calculation from a fixed corneal reference to a moving pupil-center reference that adapts to pupil size changes. By changing the reference parameter based on real-time pupil diameter measurements, the system maintains accuracy across varying light conditions where pupil size fluctuates
Solution Approach 2:
The system implements continuous feedback by monitoring pupil diameter and using this information to update the gaze estimation reference point in real-time. The pupil diameter measurement feeds back into the gaze calculation algorithm, allowing the system to compensate for pupil movement and maintain accurate tracking throughout the day
2Ease of manufacture
If a fixed calibration is performed during manufacturing, then initial setup is simple, but calibration accuracy deteriorates over time as pupil characteristics change
Solution Approach 1:
The system performs preliminary continuous calibration in the background during normal operation, collecting pupil center and diameter data to establish a personalized offset model before formal calibration is needed. This preliminary data collection simplifies subsequent calibration while ensuring long-term accuracy
Solution Approach 2:
The system maintains continuous calibration by constantly measuring pupil characteristics and updating the offset model in the background without interrupting normal operation. This continuous refinement of calibration data ensures accuracy is maintained over time without requiring repeated manual calibration procedures
3Measurement precision
If continuous measurement of pupil characteristics is performed, then gaze tracking accuracy is improved, but computational complexity increases
Solution Approach 1:
The system extracts only the essential parameter (pupil diameter) needed for compensation from the full eye image data, rather than processing all image features. By isolating and measuring only the pupil diameter alongside pupil center position, the system reduces computational complexity while maintaining the accuracy benefits of continuous adaptation
Data Source
Figure 1~2
Figure 3
Figure 4a~4b
AI summary
A method for forming an offset model is described. The offset model represents an estimated offset between a limbus center of a user eye and a pupil center of the user eye as a function of pupil size. The approach includes sampling a set of limbus center values, sampling a set of pupil center values, and sampling a set of radius values. The offset model is formed by comparing a difference between the set of limbus center values and the set of pupil center values at each of the radius values. A system and a computer-readable storage device configured to perform such a method are also disclosed.