Eye Gaze Tracking Confidence Weighting for Reliable Binocular Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye tracking systems face challenges in accurately determining gaze directions due to differences in the positioning and optical properties of the left and right eyes, which can lead to unreliable gaze tracking data when averaged without considering individual eye reliability.
Innovation Solution
An eye tracking system that determines confidence values for the reliability of gaze directions based on various parameters for each eye, such as glint position, pupil-iris contrast, and optical effects, and combines these with weighted averaging to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If gaze directions from both eyes are averaged without considering individual reliability, then the calculation is simple and fast, but the accuracy and reliability of the final gaze direction deteriorates due to differences in eye positioning and optical properties
Solution Approach 1:
The patent applies local quality by assigning different confidence values to gaze directions from the left and right eyes based on their individual reliability. Instead of treating both eyes equally, the system evaluates specific parameters (pupil-iris contrast, glint position, optical effects) for each eye separately and weights their contributions differently in the final averaged gaze direction calculation.
2Reliability
If confidence values are determined for each eye based on multiple parameters, then the reliability of gaze tracking improves, but the computational complexity and processing time increases
Solution Approach 1:
The patent implements preliminary action by pre-defining confidence value determination based on key parameters such as pupil-iris contrast, glint position, and optical effects. These confidence metrics are calculated in advance for each eye before the final gaze direction computation, allowing the system to efficiently weight and combine the gaze directions without excessive processing delays during real-time operation.
3Measurement precision
If multiple parameters are evaluated for each eye, then the distinction between reliable and unreliable gaze data improves, but the device complexity and computational load increases
Solution Approach 1:
The patent applies parameter changes by evaluating specific measurable parameters (pupil-iris contrast ratios, glint position coordinates, optical effect intensities) for each eye to determine confidence values. By transforming qualitative reliability assessments into quantitative parameter-based evaluations, the system can objectively differentiate between reliable and unreliable gaze data while maintaining manageable computational requirements through focused parameter selection.
Data Source
Figure 1~2
Figure 3
Figure 4a~4c
AI summary
Circuitry of a gaze/eye tracking system obtains one or more images of a left eye and one or more images a right eye, determines a gaze direction of the left eye based on at least one obtained image of the left eye, determines a gaze direction of the right eye based on at least one obtained image of the right eye, determines a first confidence value based on the one or more obtained images of the left eye, determines a second confidence value based on the one or more obtained images of the right eye, and determines a final gaze direction based at least in part on the first confidence value and the second confidence value. The first and second confidence values represent indications of the reliability of the determined gaze directions of the left eye and the right eye, respectively. Corresponding methods and computer-readable media are also provided.