Personalized 3D Eye Model Enrollment for Precise Gaze Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional virtual and mixed reality systems rely on generic human eye models for gaze tracking and biometric authentication, which lack personalization and accuracy, leading to suboptimal user experiences and limited design freedom.
Innovation Solution
An imaging system captures images of a user's eyes in different orientations and brightness levels to generate a personalized, user-aware eye model, eliminating the need for ground truth targets and enhancing gaze tracking and biometric authentication accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If generic human eye models are used for gaze tracking, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The system performs preliminary enrollment by capturing eye images at multiple orientations and brightness levels before actual use. This preliminary action creates a personalized eye model that stores user-specific characteristics, eliminating the need for complex real-time calculations during gaze tracking while maintaining high precision.
Solution Approach 2:
The system changes physical parameters during enrollment by displaying stimuli at multiple brightness levels and capturing images at different eye orientations. These parameter variations allow the system to build a comprehensive eye model that accurately represents how the user's eye responds to different conditions, improving measurement precision without requiring complex hardware.
2Measurement precision
If user-specific eye models are constructed from multiple images, then measurement precision improves, but loss of time increases
Solution Approach 1:
The enrollment process uses periodic stimulation by displaying images at systematically varied brightness levels and orientations. This structured periodic action efficiently captures the necessary eye responses in a limited number of steps, reducing enrollment time while ensuring comprehensive data collection for high-precision biometric authentication.
Solution Approach 2:
The system performs the time-consuming eye model construction as a preliminary enrollment step that occurs once or infrequently. The resulting personalized eye model is then stored and reused for subsequent gaze tracking and biometric authentication, achieving high precision without repeating the time-consuming measurement process.
3Manufacturing precision
If eye images are captured at multiple orientations and brightness levels, then manufacturing precision of the eye model improves, but use of energy increases
Solution Approach 1:
The system achieves high eye model accuracy by changing display parameters (brightness levels) rather than using complex hardware configurations. By systematically varying these software-controlled parameters and capturing the resulting eye responses, the system obtains precise manufacturing-level eye model data without requiring additional energy-intensive hardware components.
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 user-aware eye model improves gaze tracking precision and biometric authentication by accurately modeling the user's cornea and pupil dynamics, providing a better user experience and increased design flexibility.
Implementation Method 1
An imaging system may include two or more illumination sources (e.g., point light sources such as light-emitting diodes (LEDs)) that illuminate a person's eye or eye region, and at least one camera configured to capture images of light from the illumination sources reflected by the eye when illuminated
Implementation Method 2
Brightness of the display, or other display characteristics, may be modulated to stimulate different pupil responses
Data Source
AI summary
Methods and apparatus for generating user-aware eye models. During an enrollment process, images of a user's eye are captured by one or more cameras when the eye is in two or more different orientations and at two or more different levels of display brightness. The captured images are processed to generate a 3-dimensional, user-aware eye model, for example a model of at least the eye's cornea and pupil features. The generated user-aware eye model may be used in other processes, for example in a gaze tracking process. The enrollment process may be an iterative process to optimize the eye model, or a continuous process performed while the user is using the system.