Eye Movement Detection Using Physiological Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Eye-tracking techniques face reliability issues due to poor lighting and noise, particularly in vehicles, which affect the accuracy of determining eye movements.
Innovation Solution
A computer-implemented method using visible or infrared cameras to record eye images, generating signals based on movement parameters, and applying predetermined physiological thresholds to distinguish between eye states (open, closed, saccade, or fixation) without noise filters, thereby increasing reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If eye-tracking is performed using a camera in a vehicle, then eye movement observation is enabled, but reliability deteriorates due to bad lighting and high noise
Solution Approach 1:
The patent applies parameter changes by using multiple different thresholds for evaluating eye movement data. Instead of a single threshold, the system uses a first threshold for initial evaluation and a second threshold for re-evaluation of selected portions, adapting the evaluation parameters to improve reliability in noisy environments
Solution Approach 2:
The patent implements preliminary action by selecting a portion of the eye movement signal for re-evaluation before final determination. The system identifies and isolates specific portions of data that meet certain criteria, then applies a second evaluation with different thresholds to these selected portions before making the final eye state determination
2Object-affected harmful factors
If noise filters are applied to reduce noise, then noise is reduced, but measurement precision deteriorates due to signal distortion
Solution Approach 1:
Instead of applying noise filters that distort signals, the patent changes the evaluation parameters by using multiple different thresholds. The system evaluates eye movement data against a first threshold, then re-evaluates selected portions against a second threshold, achieving noise tolerance without signal distortion
Solution Approach 2:
The patent extracts and isolates specific portions of the eye movement signal for separate evaluation. By selecting only certain portions of the signal that meet specific criteria and evaluating them with different thresholds, the system removes the need for noise filters while maintaining measurement precision
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Computer-implemented method for determining an eye movement, the method comprising: recording a series of images of an eye of a person with a camera; generating a first signal indicative of eye openness depending on time; and for each point in time, determining whether the first signal indicates an open eye, a closed eye, or is inconclusive as to whether the eye is open or closed, depending on whether the first signal exceeds a predetermined first threshold; characterized in that the determination further depends on one or more predetermined criteria, wherein the predetermined criteria comprise minimum and maximum values for one or more of a blink duration, a number of blinks per minute, a time between blinks, and a maximum blink velocity during a movement of the eyelid when the eye is being opened and/or closed.