Driver Drowsiness Detection Using Left-Right Eye Asymmetry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing monitoring devices erroneously determine that a driver has dozed off due to sunlight glare, which affects the degree of eye opening and leads to incorrect warnings.
Innovation Solution
A determining device that analyzes the difference in eye opening between the left and right eyes, along with brightness conditions, to accurately distinguish between glare and actual drowsiness, using a processor to determine if the absolute value of this difference exceeds a reference threshold and adjusts thresholds based on face brightness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the monitoring device determines drowsiness based solely on eye opening degree, then the detection simplicity is improved, but the reliability of drowsiness detection deteriorates due to false alarms from sunlight glare
Solution Approach 1:
The patent applies asymmetry by comparing the eye opening degrees between the left and right eyes. When sunlight glare affects the driver's face, it typically affects one eye more than the other, creating an asymmetric pattern. The determination unit calculates the absolute difference between left and right eye opening degrees, and when this difference exceeds a threshold, it identifies glare conditions and excludes them from drowsiness detection, thereby maintaining high reliability while keeping the detection method relatively simple.
2Reliability
If the monitoring device uses additional parameters like brightness and eye difference to improve detection accuracy, then the reliability of drowsiness detection is improved, but the device complexity increases
Solution Approach 1:
The patent segments the drowsiness detection process into distinct stages: first determining whether glare is present by comparing left and right eye opening degrees, and then based on that determination, either adjusting the eye opening threshold or excluding the measurement entirely. This segmentation allows the system to use additional parameters (eye difference, brightness) only when necessary to improve reliability, while maintaining a relatively simple algorithm structure through conditional branching rather than continuous complex calculations.
Data Source
AI summary
A determining device has a processor configured to determine that a driver has dozed off when degree of eye opening of a left eye and degree of eye opening of a right eye of the driver are at or below a reference degree of eye opening and an absolute value of difference between the degree of eye opening of the left eye and the degree of eye opening of the right eye does not exceed a reference difference or determine that the driver has not dozed off when the degree of eye opening of the left eye and the degree of eye opening of the right eye are at or below the reference degree and the absolute value of the difference between the degree of eye opening of the left eye and the degree of eye opening of the right eye exceeds a reference difference during a determining period.