Pupil Radius Compensation for Eye Tracking Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye tracking systems face inaccuracies due to variations in pupil size, which affect the angular offset between eye direction and gaze direction, especially under varying lighting conditions, impacting performance in dynamic environments like virtual and augmented reality.
Innovation Solution
A method and system that determine the angular offset between eye and gaze directions using a compensation model based on measured pupil sizes, allowing for improved gaze tracking accuracy by accounting for pupil size variations, and dynamically updating this model during calibration processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional eye tracking methods are used without pupil size compensation, then the system structure remains simple, but gaze tracking accuracy deteriorates under varying lighting conditions
Solution Approach 1:
The patent applies parameter changes by introducing pupil size as a compensating parameter. The system measures pupil size and uses it to adjust the angular offset calculation, thereby compensating for lighting condition variations. This resolves the contradiction by adding a measurable parameter (pupil size) that improves accuracy without requiring fundamental system restructuring.
Solution Approach 2:
The patent replaces complex mechanical or hardware adjustments with a computational model. Instead of physically adjusting the eye tracking system for different lighting conditions, it substitutes a mathematical compensation model that calculates corrected gaze directions based on pupil size measurements, simplifying the overall system while maintaining accuracy.
2Measurement precision
If a fixed angular offset model is used, then the calculation process remains simple, but tracking accuracy deteriorates when pupil size varies
Solution Approach 1:
The patent transitions from a static fixed angular offset model to a dynamic model where the angular offset varies with pupil size. The system continuously adapts the offset value based on real-time pupil size measurements, allowing accurate tracking across different lighting conditions while maintaining a relatively simple calculation framework.
Solution Approach 2:
The patent changes the angular offset parameter dynamically based on pupil size. Instead of using a constant offset value, the system adjusts this parameter according to measured pupil dimensions, improving accuracy without requiring a completely complex calculation model.
3Reliability
If pupil size compensation is implemented, then robustness under varying lighting conditions improves, but system complexity increases
Solution Approach 1:
The patent replaces physical or hardware-based adaptation mechanisms with a computational compensation approach. The system uses software-based pupil size measurement and angular offset adjustment to achieve robustness against lighting changes, avoiding the need for complex mechanical adjustments or multiple hardware configurations.
Solution Approach 2:
The patent introduces pupil size as an additional measurement parameter to compensate for lighting variations. By monitoring and adjusting based on this parameter, the system achieves improved reliability under varying conditions without requiring fundamental changes to the hardware architecture.
Data Source
Figure 1~2
Figure 3
Figure 4a~4b
AI summary
A method is disclosed, comprising obtaining a first angular offset between a first eye direction and a first gaze direction of an eye having a first pupil size, obtaining a second angular offset between a second eye direction and a second gaze direction of the eye having a second pupil size, and forming, based on the first angular offset and the second angular offset, a compensation model describing an estimated angular offset as a function of pupil size. A system and a device comprising a circuitry configured to perform such a method are also disclosed.