Gaze Detection Using Pupil-Glint Geometry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional eye tracking methods for determining user gaze direction are computationally intensive and inaccurate when the user or display apparatus moves, as they require complex calculations and are not effective in detecting if the gaze is directed forward.
Innovation Solution
A display apparatus and method using an infrared outputter, image capturer, and controller to detect the pupil, iris, and glint area, determining the gaze direction based on the relationship between the pupil and glint area, and the size of the iris, with threshold comparisons to determine if the gaze is directed forward, reducing computational load and movement influence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional eye tracking methods use complex calculation to analyze glint and pupil, then measurement precision of gaze direction is improved, but device complexity and computational load increase
Solution Approach 1:
The patent extracts only the essential information needed for gaze direction determination (pupil center position and glint position) from the eye image, rather than performing comprehensive analysis of all eye features. This selective extraction simplifies the calculation while maintaining measurement precision by focusing on the key geometric relationship between pupil and glint positions.
Solution Approach 2:
Instead of calculating gaze direction through complex multi-step analysis of eye features, the patent inverts the approach by directly using the geometric relationship between detected features (pupil center and glint) to determine gaze direction. This inverted simplification reduces computational complexity while preserving measurement accuracy.
2Measurement precision
If conventional eye tracking methods perform detailed analysis, then measurement precision is improved, but reliability under movement conditions deteriorates
Solution Approach 1:
The patent extracts only the critical geometric relationship (distance and angle between pupil center and glint) needed for gaze determination, eliminating unnecessary detailed analysis that would be sensitive to movement. This extraction approach maintains precision while improving reliability under movement conditions by focusing on invariant geometric properties.
Solution Approach 2:
The patent changes the measurement parameters from detailed eye feature analysis to simple geometric parameters (distance and angle between pupil and glint). These parameter changes make the measurement more robust to movement while maintaining the ability to accurately determine gaze direction through threshold comparisons.
3Measurement precision
If conventional eye tracking methods use complex calculation, then measurement precision is improved, but processing speed deteriorates
Solution Approach 1:
The patent extracts only the essential geometric parameters (pupil center position, glint position, distance between them, and angle) from eye images, avoiding complex calculations. This extraction enables rapid processing while maintaining measurement precision through simple distance and angle computations that can be performed quickly.
Solution Approach 2:
The patent performs only the necessary partial analysis (detecting pupil center and glint positions and calculating their geometric relationship) rather than comprehensive eye analysis. This partial action approach achieves sufficient measurement precision with significantly reduced processing time and computational resources.
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
Accurately determines if the user's gaze is directed forward with reduced computational load and robustness against movement, enabling efficient operation and accurate functionality.
Implementation Method 1
an infrared outputter configured to output infrared light toward a user
Implementation Method 2
a glint area generated by the infrared light
Data Source
AI summary
A display apparatus includes an infrared outputter configured to output infrared light toward a user, an image capturer configured to photograph the user to generate a captured image, and a controller configured to detect, from the captured image, a pupil and an iris of the user, and a glint area generated by the infrared light, and to determine, in response to the pupil, the iris, and the glint area being detected, a direction of the user's gaze based on a relation between a location of the pupil, and the glint area, and a size of the iris.