Eye Tracking Device Limbus Triangulation 3D Gaze
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current eye tracking technologies face limitations in accuracy, precision, and flexibility due to their inability to measure six degrees of freedom of eye movement and track visual features effectively, particularly due to distortion caused by the corneal lens and lack of well-defined features in the limbus region.
Innovation Solution
An eye tracking method and device that uses triangulation of the geometrical representation of the limbus structure from multiple images to determine three-dimensional position and gaze direction, employing digital image pre-processing and machine learning to identify stable regions and calculate limbus parameters without requiring user calibration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional eye tracking methods (contact lenses, EOG, PSD) are used, then angular eye movements can be measured, but lateral eye shifts cannot be measured and head stabilization is required
Solution Approach 1:
The patent transitions from 2D angular measurement to 3D spatial measurement by capturing images from multiple viewpoints and performing triangulation. This allows measurement of both angular movements and lateral shifts by determining the three-dimensional position of eye features in space, resolving the limitation of traditional single-plane measurement methods.
Solution Approach 2:
The patent replaces mechanical contact methods (contact lenses, suction cups) and stationary PSD systems with an optical image-based system. This substitution enables non-intrusive measurement without requiring head stabilization, as the system captures images and processes them computationally to determine eye position and gaze direction.
2Ease of operation
If VOG systems with infra-red illumination are used, then non-intrusive eye tracking is achieved, but frame rate is limited due to exposure requirements
Solution Approach 1:
The patent performs digital image pre-processing to enhance the limbus structure before triangulation. By preprocessing the images to improve contrast and definition of the limbus, the system can achieve accurate measurements with standard exposure times, thereby maintaining high frame rates while keeping the operation non-intrusive.
3Loss of information
If pupil and iris features are tracked, then eye movement data can be extracted, but features are distorted by the corneal lens and vary between individuals
Solution Approach 1:
The patent extracts and tracks the limbus structure instead of relying on pupil and iris features. The limbus is extracted as a distinct geometric feature that can be triangulated across multiple images. This extraction approach avoids the distortion problems of corneal lens effects on pupil/iris while providing stable, measurable features for accurate eye movement tracking.
4Measurement precision
If the limbus region is tracked, then undistorted features are available, but the limbus lacks well-defined features for classical image processing
Solution Approach 1:
The patent performs digital image pre-processing specifically designed to enhance the limbus structure. This preliminary action includes operations that improve the contrast and geometric definition of the limbus in the captured images, making it suitable for triangulation and geometric analysis despite the original lack of well-defined features.
Solution Approach 2:
The patent changes the parameters of the limbus structure through digital image processing to improve its detectability. By applying preprocessing operations that enhance edge definition and contrast, the limbus transforms from a poorly defined region into a feature with sufficient geometric clarity for accurate triangulation and measurement.
Data Source
AI summary
The presently disclosed subject matter relates to an eye tracking method and device. The method can include receiving image data indicative of at least two images of a user's eye, identifying, in each image, regions related to the eye limbus; determining geometrical representation of the limbus structure, and determining a three-dimensional position and gaze direction of the user's eye (i.e. full six degrees of freedom of the eye) by triangulation of the geometrical representation of the limbus structure of at least two images.