Gaze Tracker Calibration Using Expected vs Measured Gaze
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Gaze trackers in devices can become inaccurately calibrated due to movement or slippage, leading to erroneous inputs and unpredictable device operations.
Innovation Solution
A method and system for adjusting the calibration parameter of a gaze tracker in real-time by comparing an expected gaze position with a measured gaze position, using characteristic values of displayed visual elements, and updating the calibration parameter to maintain accuracy without requiring user intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If gaze tracker calibration is performed manually with user intervention, then measurement precision is improved, but device complexity and ease of operation deteriorate due to disruptive re-calibration prompts
Solution Approach 1:
The system performs automatic calibration without user intervention by detecting gaze targets independently. The processor determines calibration parameters by analyzing the relationship between displayed visual elements and measured gaze positions, eliminating the need for manual user participation in the calibration process.
Solution Approach 2:
The system continuously monitors gaze tracking accuracy by comparing measured gaze positions with expected gaze positions based on visual element characteristics. When deviations are detected, the system automatically adjusts calibration parameters to correct the accuracy issues, creating a closed-loop feedback mechanism.
2Measurement precision
If real-time calibration adjustment is implemented, then measurement precision is maintained, but device complexity increases due to continuous background operations
Solution Approach 1:
The existing gaze tracking components (image sensor, display, processor) are made to serve dual purposes: normal gaze tracking operation and automatic calibration. The same hardware infrastructure is used for both measuring gaze and determining calibration parameters, eliminating the need for separate dedicated calibration hardware.
Solution Approach 2:
The system performs calibration adjustments proactively based on detected deviations before they significantly impact user experience. By continuously monitoring and adjusting calibration parameters in the background, the system prevents accuracy degradation rather than reacting to severe errors.
3Reliability
If continuous background calibration is performed, then reliability is improved, but use of energy increases due to ongoing processing operations
Solution Approach 1:
Instead of continuous intensive calibration processing, the system performs calibration adjustments periodically based on detected needs. Calibration operations are triggered when specific conditions are met (e.g., when gaze position deviations exceed thresholds), rather than running continuously at full intensity.
Solution Approach 2:
The system performs calibration adjustments only to the extent necessary to correct detected deviations. Rather than performing full calibration routines continuously, the system applies minimal necessary adjustments to maintain acceptable accuracy levels, reducing energy consumption while preserving reliability.
Data Source
AI summary
A method includes displaying a plurality of visual elements. The method includes determining, based on respective characteristic values of the plurality of visual elements, an expected gaze target that indicates a first display region where a user of the device intends to gaze while the plurality of visual elements is being displayed. The method includes obtaining, via the image sensor, an image that includes a set of pixels corresponding to a pupil of the user of the device. The method includes determining, by a gaze tracker, based on the set of pixels corresponding to the pupil, a measured gaze target that indicates a second display region where the user is measuredly gazing. The method includes adjusting a calibration parameter of the gaze tracker based on a difference between the first display region indicated by the expected gaze target and the second display region indicated by the measured gaze target.