Eye-Gaze Detection Displacement Correction via Corneal Vector Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Eye-gaze detection systems face accuracy issues when the head-mounted display is physically displaced, as the relative positional relationship between the user and the display changes, leading to decreased detection accuracy.
Innovation Solution
An eye-gaze detection system that includes a plurality of illumination units to illuminate the user's eyes with invisible light, a camera to capture images, a pupil specifying unit to identify the pupil center, an obtaining unit to determine the corneal curvature center based on illumination positions and camera placement, and a displacement detection unit to detect changes in the mounting state by analyzing vectors between these points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If calibration is performed in advance for eye-gaze detection, then detection accuracy is improved under fixed mounting conditions, but detection accuracy deteriorates when the head mounted display is physically displaced
Solution Approach 1:
The system performs preliminary calibration to establish the initial mapping between eye position and gaze direction. This calibration data is stored and used as a baseline, allowing the system to later detect deviations caused by displacement and compensate for them dynamically.
Solution Approach 2:
The system continuously monitors the vector between pupil center and corneal curvature center, comparing it against the calibrated baseline. When displacement is detected through feedback from this vector change, the system automatically corrects the gaze detection algorithm to maintain accuracy despite mounting variations.
2Ease of operation
If the head mounted display is mounted on the user's head, then portability and ease of operation are improved, but the relative positional relationship becomes unstable leading to detection errors
Solution Approach 1:
The system transitions from a static calibration approach to a dynamic adaptation mechanism. It continuously tracks changes in the corneal curvature center position and adjusts the gaze detection parameters in real-time, allowing the system to maintain accuracy despite the dynamic and variable mounting conditions on the user's head.
Solution Approach 2:
The system changes the detection parameters dynamically by calculating the displacement vector between the pupil center and corneal curvature center. This vector information is used to adjust the gaze detection algorithm parameters, enabling the system to adapt to varying mounting positions and maintain detection accuracy.
3Measurement precision
If multiple illumination units are used to illuminate the eye with invisible light, then the ability to detect corneal curvature improves, but device complexity increases
Solution Approach 1:
The illumination system is segmented into multiple discrete illumination units positioned at known locations. Each unit independently illuminates the cornea from a specific angle, and the camera captures the reflected light patterns. This segmentation allows the system to calculate the corneal curvature center by analyzing the geometric relationships between multiple illumination points and their corresponding reflections, improving measurement precision through multi-point validation.
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
The system effectively detects displacement of the head-mounted display, allowing for accurate gaze position correction and maintaining detection accuracy even when the display is moved.
Implementation Method 1
a plurality of illumination units configured to illuminate an eye of the user with invisible light
Implementation Method 2
a camera configured to capture the eye of the user on the basis of the invisible light
Data Source
AI summary
An eye-gaze detection system containing a mounting tool mounted on a user for use, includes: plural illumination units illuminating an eye of the user with invisible light; a camera capturing the eye on the basis of the invisible light; a pupil specifying unit specifying a pupil center of the user from a captured image having been captured; an obtaining unit obtaining information on a position of a center of a corneal curvature of the user on the basis of disposed positions of the illumination units and the camera, and illuminated positions by illumination light emitted from the illumination units to the eye; a vector specifying unit specifying a vector connecting the center of the corneal curvature and the pupil center on the captured image; and a displacement detection unit detecting displacement of a mounting state of the mounting tool mounted on the user on the basis of the vector.