Drowsy State Determination Device Using Dual Eye-Closure Thresholds
Solution Overview
Problem
Existing drowsiness detection devices for drivers are prone to erroneous determinations due to their inability to differentiate between multiple levels of drowsiness and are influenced by factors like bright light, leading to incorrect assessments of the driver's state as either awake or dozing.
Innovation Solution
A drowsy state determination device that uses a combination of first and second thresholds to differentiate eye closure durations and frequencies, allowing for the differentiation of drowsiness levels into multiple states, including slight and heavy drowsiness, by calculating an eye-closure value based on these thresholds and adjusting them according to vehicle speed and travel time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single threshold is used to determine drowsiness based on accumulated eye closure duration, then the device is simple to operate, but the measurement precision of drowsiness level is poor
Solution Approach 1:
The patent divides the drowsiness determination into multiple stages using a first threshold for eye closure duration and a second threshold for occurrence frequency. This segmentation allows differentiation of drowsiness levels by evaluating multiple criteria sequentially, improving measurement precision without excessive complexity
Solution Approach 2:
The patent transitions from a single-dimensional threshold (accumulated duration only) to a two-dimensional threshold system (duration × frequency). By adding the frequency dimension of eye closure occurrences, the system achieves more precise drowsiness level differentiation while maintaining reasonable device complexity
2Measurement precision
If the threshold is set to detect dozing state, then heavy drowsiness can be detected, but slight drowsiness cannot be differentiated
Solution Approach 1:
The patent applies partial action by using the first threshold to filter eye closures of sufficient duration, then applying the second threshold to the frequency of these filtered closures. This staged approach enables differentiation of slight drowsiness (lower frequency) from heavy drowsiness (higher frequency) while keeping the classification system manageable
3Measurement precision
If the threshold is optimized for accuracy, then drowsiness detection precision improves, but false determination occurs under bright light conditions
Solution Approach 1:
The patent introduces an intermediary filtering mechanism where the first threshold acts as a gatekeeper, selecting only eye closures of sufficient duration before frequency analysis. This intermediary step prevents brief eye closures due to bright light from triggering false drowsiness determinations, while still capturing genuine drowsiness patterns
Data Source
AI summary
A blink detection section generates an eye-closure signal indicating the duration of a period for which the driver closes his/her eyes. An eye-closure count section calculates the respective occurrence frequencies of single eye closures in a prescribed measurement period for a first eye-closure period threshold and a second eye-closure period threshold, based on the eye-closure signal and the respective eye-closure period thresholds. A drowsy state determination section compares the respective occurrence frequencies with the first eye-closure frequency threshold and the second eye-closure frequency threshold to determine which of the drowsiness levels corresponding to the respective thresholds the drowsiness level of the driver is at.