Adaptive Eye Feature Mapping for Real-Time Fatigue Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing pilot monitoring systems face challenges in accurately mapping eye features to fatigue estimates due to inadequate geometric models for eye tracking, leading to inefficiencies in fatigue monitoring.
Innovation Solution
A computer system that records eye tracking data, identifies movements, and iteratively refines associations between eye features and basic geometric shapes, deriving performance metrics and fatigue estimations in real-time, using machine learning algorithms to enhance accuracy and adaptiveness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional geometric models are used for eye tracking, then the system structure is simple, but the measurement precision of eye features is insufficient
Solution Approach 1:
The patent implements dynamic geometric models that are continuously refined through iterative processing of eye tracking data. The system starts with initial geometric associations and progressively improves them by analyzing movements and adjusting parameters, transforming static models into adaptive, dynamic structures that enhance measurement precision without requiring complete model redesign
Solution Approach 2:
The system employs feedback mechanisms where eye tracking data is continuously processed to refine geometric model associations. The measured eye feature positions and movements feed back into the model, allowing automatic adjustment and optimization of geometric parameters, thereby improving measurement accuracy through iterative learning from actual data
2Measurement precision
If complex geometric models are used to improve eye feature mapping, then measurement precision improves, but processing time increases
Solution Approach 1:
The patent pre-establishes geometric associations between eye features and geometric shapes before actual eye tracking begins. These preliminary models provide a ready framework that enables rapid feature identification during operation, avoiding the need for complex real-time calculations while maintaining high measurement precision through pre-computed geometric relationships
Solution Approach 2:
The system segments the eye tracking analysis into distinct geometric components (pupil, iris, eyelids, etc.), each associated with specific geometric shapes. This segmentation allows independent processing of each feature, reducing overall computational complexity while maintaining accurate measurement of individual eye features through dedicated geometric models
3Adaptability or versatility
If static geometric associations are used, then the system is simple to implement, but adaptability to different eye movements is poor
Solution Approach 1:
The patent transforms static geometric associations into dynamic models that automatically adapt to different eye movements and individual variations. The system continuously refines geometric parameters based on observed eye tracking data, enabling the model to adjust to various eye characteristics and movement patterns without manual reconfiguration, thereby achieving high adaptability through dynamic parameter optimization
Data Source
AI summary
A computer system records eye tracking data and identifies movements in the eye tracking data to create and iteratively refine associations between eye features and basic geometric shapes. The associations are used to rapidly identify eye features for eye tracking. The system derives performance metrics and fatigue estimations from the identified basic geometric shapes, including changes in such shapes over time. The system continuously adjusts and/or weights the associations in real-time based on eye tracking data.