Eye Gaze Metrics for Real-Time Psychophysiological State Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing driver monitoring systems face challenges in accurately and non-intrusively assessing psychophysiological states such as fatigue, drowsiness, and stress due to the computational complexity of interpreting eye gaze data in real-time, often relying on intrusive sensors that are uncomfortable for drivers and provide inaccurate assessments.

Innovation Solution

A method and system that captures eye gaze vectors and eyelid openness levels to derive second order eye movement metrics, transforming them into a compact, machine-readable representation for real-time prediction of psychophysiological states using machine learning models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional physiological sensors are used to monitor psychophysiological state, then measurement accuracy is improved, but device complexity and driver comfort deteriorate due to intrusive sensors

Engineering Contradiction:
Improvepsychophysiological state assessment accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces intrusive physiological sensors with an optical-based eye tracking system that uses a camera to capture eye gaze vectors and eyelid openness levels. This substitution eliminates the need for physical contact with the driver's body while still enabling psychophysiological state detection through analysis of eye movement patterns

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces eye gaze data as an intermediary measure that indirectly reflects psychophysiological states. Instead of directly measuring physiological parameters like heart rate or brain activity, the system uses eye movement metrics (gaze direction, fixation duration, saccade frequency) as a mediator to infer cognitive load, stress, and fatigue levels

Inventive Principle:
Principle #24Intermediary (Mediator)

2Speed

If eye gaze data is processed in real-time to detect psychophysiological states, then response time is improved, but computational complexity increases

Engineering Contradiction:
Improvestate detection response timeVSAvoidcomputational processing complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent extracts only the most relevant features from eye gaze data for real-time processing. Instead of analyzing all raw eye movement data, the system selectively processes key metrics such as fixation duration, saccade frequency, and gaze dispersion, which have been identified as strong indicators of psychophysiological states. This extraction reduces computational burden while maintaining detection accuracy

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the eye gaze data processing into distinct analytical components: (1) capturing eye gaze vectors and eyelid openness levels, (2) calculating second-order eye movement metrics, (3) transforming metrics into machine-readable representations, and (4) predicting psychophysiological states using trained models. This segmentation enables parallel processing and optimizes computational efficiency for real-time operation

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4628002A1Methods and systems for eye gaze metric determination and psychophysiological state detection
Publication Date: 2025.10.08 HARMAN INT IND INC
  • EP4628002A1 patent drawingFigure 1
  • EP4628002A1 patent drawingFigure 2
  • EP4628002A1 patent drawingFigure 3

AI summary

Disclosed herein are methods and systems for real-time detection of psychophysiological states from eye movement data. The methods involve capturing eye gaze vectors and eyelid openness levels over time using a user-facing camera (240). A sequence of discrete eye behaviors, including saccades, fixations, blinks, and long closures, is determined (304) from the eye gaze vectors and eyelid openness levels. The sequence of discrete eye behaviors is transformed (308) into a machine readable representation using a sliding time window. A mathematical or machine learning model (214) then maps the machine readable representation of eye behaviors to one or more psychophysiological states (310). This approach provides a computationally efficient mechanism for predicting psychophysiological states by compressing gaze data into a continuous, numerical representation of eye behavioral events correlated with human psychophysiological states, including drowsiness, cognitive load, stress, and others.