Driver Sleepiness Detection Using Adaptive Eyelid Threshold Reset
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sleepiness detection devices face challenges in accurately determining sleepiness in drivers during vehicle operation, particularly due to individual and situational variations in eyelid opening/closing characteristics, and the need for frequent resetting of threshold values after interruptions, which can lead to erroneous judgments and delayed detection.
Innovation Solution
A device that assesses the necessity for resetting threshold values based on changes in the driver's condition after interruptions, using time intervals between eyelid transitions and statistical measures like standard deviation or variance to determine sleepiness, and sets multiple threshold values for different stages of sleepiness, allowing for continuous detection without unnecessary resets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If threshold values are frequently reset after interruptions to maintain detection accuracy, then measurement precision is improved, but loss of time increases due to detection suspension during resetting
Solution Approach 1:
The system performs preliminary actions by collecting eyelid opening/closing characteristic amounts during normal driving periods before interruptions occur. This accumulated data is then used to quickly reset threshold values after interruptions, reducing the time needed for threshold re-establishment and minimizing detection suspension.
Solution Approach 2:
The system implements feedback by continuously monitoring eyelid characteristics during driving, comparing them against dynamically adjusted threshold values. After interruptions, the system uses feedback from pre-interruption data to rapidly recalibrate thresholds, maintaining detection accuracy while minimizing time loss.
2Reliability
If threshold values are reset after every interruption to maintain accuracy, then reliability is improved, but productivity decreases due to reduced detection availability
Solution Approach 1:
The system performs preliminary data collection and threshold preparation during normal driving periods before interruptions. This allows the system to maintain high reliability after interruptions by using pre-prepared threshold values, thereby avoiding prolonged detection suspension and maintaining productivity.
Solution Approach 2:
The system dynamically adjusts threshold resetting strategies based on interruption characteristics. For short interruptions, it uses rapid threshold restoration from pre-collected data, while for longer interruptions, it performs more comprehensive recalibration, optimizing both reliability and productivity across different scenarios.
3Measurement precision
If individual variations in eyelid characteristics are accounted for by setting personalized threshold values, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system implements self-service by automatically collecting eyelid characteristic data from each driver during normal driving and autonomously generating personalized threshold values. This eliminates the need for manual calibration or complex user setup, achieving individualized detection accuracy while keeping the interface simple and the overall system complexity manageable.
Solution Approach 2:
The system performs preliminary individualized calibration by collecting eyelid characteristics during initial driving periods or before interruptions. This pre-established personalized baseline data enables accurate threshold setting without requiring complex real-time adjustments, reducing perceived complexity while maintaining high measurement precision.
Data Source
Figure 1A~1B
Figure 2A~2C
Figure 3A~3C
AI summary
A device for detecting the sleepiness of a driver driving a vehicle is designed to determine if the resetting of threshold values for detection of sleepiness is performed based upon its necessity when an interruption of the driving occurs. The inventive device computes successively an eyelid opening/closing characteristic amount from time intervals between transitions between an opened state and a closed state of an eyelid detected successively; sets threshold values using the eyelid opening/closing characteristic amounts obtained in a predetermined period; and judges the driver feels sleepiness when the eyelid opening/closing characteristic amount deviates from a range defined with the threshold values. In restarting the driving after its interruption, it is judged if the resetting of the threshold values is to be performed based on the driver's condition till then, and the resetting is performed, using eyelid opening/closing characteristic amounts obtained after the restarting of the driving.