Eye Movement Tracking Using Ambient Glints and Head Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing head-mounted displays (HMDs) face challenges in accurately determining eye movement, as they struggle to differentiate between head movement and orbital eye movement, leading to inaccuracies in tracking user gaze within their field of view.
Innovation Solution
The method involves analyzing eye-image data and head-movement data using an expectation maximization process to estimate and adjust the head-movement and orbital components of eye movement, ensuring accurate tracking by comparing observed and expected movements of reflected images on the corneal surface, with recursive adjustments until a threshold difference is met.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If head-movement data is used to determine eye movement, then gaze tracking can be implemented, but accuracy deteriorates due to inability to differentiate head movement from orbital eye movement
Solution Approach 1:
The patent segments eye movement into two distinct components: head-movement component and orbital eye-movement component. By analyzing reflected image movement and separately determining the head-movement component from head-movement data, the system isolates the orbital eye-movement component through subtraction, thereby achieving accurate eye movement measurement while maintaining operational capability.
Solution Approach 2:
The system employs an expectation-maximization process that uses feedback loops to iteratively refine the separation of head-movement and orbital components. The observed movement of reflected images is compared against expected movement based on head-movement data, and the difference feedback is used to adjust and improve the accuracy of component separation until convergence is achieved.
2Measurement precision
If reflected image analysis is used to determine eye movement, then orbital eye movement can be detected, but reliability deteriorates due to contamination from head movement
Solution Approach 1:
The patent extracts the head-movement component from the total observed eye movement by utilizing independent head-movement data. This extracted component is then removed from the reflected image analysis results, leaving only the pure orbital eye-movement component. This extraction process eliminates the contaminating effect of head movement, thereby improving measurement reliability.
Solution Approach 2:
The system performs preliminary determination of the head-movement component before finalizing the orbital eye-movement measurement. By pre-calculating and removing the head-movement contribution from the observed reflected image movement, the system ensures that subsequent orbital movement analysis is not contaminated by head movement artifacts.
3Device complexity
If simple head-movement tracking is implemented, then device complexity is reduced, but measurement precision deteriorates due to sensor inaccuracies
Solution Approach 1:
The patent merges multiple data sources and analysis methods: reflected image movement analysis, head-movement sensor data, and expectation-maximization computational processing. By combining these elements into an integrated system, the patent achieves high measurement precision while maintaining reasonable device complexity through unified processing architecture.
Solution Approach 2:
The expectation-maximization process serves as an intermediary computational layer that reconciles data from different sources (reflected image analysis and head-movement sensors). This intermediary processing step corrects for sensor inaccuracies and coordinates the multiple inputs to produce accurate eye movement measurements without requiring overly complex hardware.
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 enables precise determination of eye movement, improving the accuracy of gaze tracking and reducing errors caused by sensor inaccuracies, thereby enhancing the functionality of HMDs in applications like augmented and virtual reality.
Implementation Method 1
analyzing eye-image data to determine observed movement of a reflected image over a predetermined period, wherein the reflected image is reflected from an eye
Data Source
AI summary
A method may involve analyzing eye-image data to determine observed movement of a reflected image over a predetermined period, using head-movement data to determine a first eye-movement component corresponding to head movement during the predetermined period, determining a first expected movement of the reflected image corresponding to the first eye-movement component, determining a second eye-movement component based on a difference between the observed movement and the first expected movement, determining a second expected movement of the reflected image based on the combination of the first eye-movement component and the second eye-movement component, determining a difference between the observed movement and the second expected movement, if the difference is less than a threshold, setting eye-movement data for the predetermined period based on the second eye-movement component; and if the difference is greater than the threshold, adjusting the first eye-movement component and repeating the method with the adjusted first eye-movement component.