Adaptive Gaze Filter for Eye Tracking Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Eye tracking systems face a trade-off between precision and latency, as low-pass filters improve precision but add latency, making them less responsive for detecting eye movements.
Innovation Solution
A method that determines whether the eye is in fixation or not, applying a filter to decrease variance in the gaze signal only when the eye is stationary, thereby maintaining precision without adding latency during eye movement detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a low-pass filter is applied to the gaze signal, then measurement precision is improved, but response speed deteriorates due to added latency
Solution Approach 1:
The patent applies a dynamic filtering approach where the filter is selectively applied only during fixation periods and removed during saccadic movements. This makes the filtering system adaptive rather than static, allowing it to optimize precision during stable periods while maintaining responsiveness during movement periods.
Solution Approach 2:
The filter is applied periodically during fixation periods and removed during saccadic periods. This periodic application of filtering based on eye movement state allows the system to achieve precision benefits when needed while maintaining speed during movement phases.
2Measurement precision
If a low-pass filter is applied continuously, then gaze signal noise is decreased, but detection latency increases for eye movements
Solution Approach 1:
The patent segments the eye tracking signal into distinct phases: fixation periods and saccadic periods. During fixation periods, the filter is applied to reduce noise and improve precision. During saccadic periods, the filter is removed to enable fast detection of eye movements without latency.
Solution Approach 2:
The filtering operation dynamically switches between applied and not applied based on the detected eye movement state. This dynamic control eliminates continuous filtering latency while maintaining precision benefits during stable fixation periods.
Data Source
AI summary
A method for processing a gaze signal in an eye tracking system is provided. The method comprises receiving a first image of a user's eye captured at a first point in time and a second image of the users eye captured at a second point in time subsequent to the first point in time, and determining, based on the first image and the second image, whether eye movement of the user's eye is in fixation or not. The method may further comprise to, on condition that the eye movement of the users eye is in fixation, applying a filter on the gaze signal, wherein the filter is adapted to decrease variance in the gaze signal.