Eye Tracking Mode Switching for Glint Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye tracking systems in wearable heads-up displays face challenges in accurately tracking gaze due to movements of the display, leading to instability in glint data, which affects the reliability of gaze position estimation.
Innovation Solution
The method involves tracking the gaze in a first mode using glint center data, transforming it into a frequency domain to assess stability, and switching to a second mode using glint-pupil vector tracking if instability is detected, thereby reducing the impact of display movements on gaze estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If glint center tracking mode is used, then tracking simplicity is maintained, but gaze estimation reliability deteriorates when display movements cause glint instability
Solution Approach 1:
The system dynamically switches between glint center tracking mode and glint-pupil vector tracking mode based on detected glint stability. When display movements cause glint instability, the system transitions from the simpler glint center mode to the more robust glint-pupil vector mode, thereby maintaining reliability while adapting to changing conditions.
Solution Approach 2:
The system changes the tracking parameter from glint center position to glint-pupil vector when glint stability deteriorates due to display movements. This parameter change allows the system to maintain accurate gaze estimation under varying display motion conditions by selecting the appropriate tracking parameter based on current stability characteristics.
2Reliability
If glint-pupil vector tracking mode is used, then gaze estimation reliability improves under display movements, but tracking complexity increases
Solution Approach 1:
The system employs dynamic mode switching that activates the more complex glint-pupil vector tracking only when necessary - specifically when glint instability is detected due to display movements. During stable conditions, the simpler glint center tracking mode remains active, thus avoiding unnecessary complexity while maintaining reliability when needed.
Solution Approach 2:
The system changes tracking parameters from simple glint center position to the more complex glint-pupil vector only when glint stability analysis indicates display movement interference. This conditional parameter change ensures that increased tracking complexity is applied only when it provides actual benefit to gaze estimation reliability.
3Measurement precision
If frequency domain transformation is applied to assess glint stability, then detection accuracy improves, but processing time increases
Solution Approach 1:
The system applies frequency domain transformation (such as Fourier transform) to glint data to accurately assess stability characteristics. By transforming the time-domain glint position data into frequency domain, the system can identify periodic patterns and stability metrics that are not apparent in the time domain, thereby improving detection accuracy despite the additional processing required.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the robustness of eye tracking by adapting to instability caused by display movements, providing a more reliable estimate of gaze position through dynamic mode switching, reducing errors and inconsistencies.
Implementation Method 1
obtaining glint data of at least one glint of the eye during at least a portion of tracking the gaze of the eye in the first tracking mode
Implementation Method 2
transforming the glint data into a frequency domain to generate a glint frequency spectrum
Data Source
AI summary
A method of tracking a gaze of an eye includes tracking the gaze of the eye in a first tracking mode. Glint data of at least one glint of the eye is obtained during at least a portion of tracking the gaze of the eye in the first tracking mode. The glint data is in a time domain and includes a time series of a spatial descriptor associated with the at least one glint. The glint data is transformed into a frequency domain to generate a glint frequency spectrum. A stability of the at least one glint is determined based on the glint frequency spectrum. If the at least one glint is determined to be unstable, tracking of the gaze of the eye is switched from the first tracking mode to a second tracking mode that is different from the first tracking mode.