Drowsiness Detection Device with Adaptive PERCLOS Threshold
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing drowsiness detection systems face challenges in accurately detecting drowsiness due to personal differences in eye lid closure (PERCLOS) rates, as a uniformly set threshold value may not suit individual drivers, leading to inaccurate detection.
Innovation Solution
A drowsiness detection device with a camera and control unit that calculates PERCLOS and adjusts the threshold value based on initial eye closure and blinking patterns, allowing for personalized threshold setting to improve detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a uniformly set threshold value is used for PERCLOS detection, then the detection system is simple to implement, but detection accuracy deteriorates due to personal differences in eye closure patterns
Solution Approach 1:
The system performs preliminary measurement of the driver's baseline PERCLOS value before actual drowsiness detection begins. This preliminary action establishes individual-specific characteristics that are then used to set personalized threshold values, thereby improving detection accuracy without complicating the overall system implementation
Solution Approach 2:
The threshold value parameter is dynamically adjusted based on individually measured baseline PERCLOS data. Instead of using a fixed uniform threshold, the system changes the threshold parameter to match each driver's eye closure characteristics, resolving the contradiction between simple implementation and accurate detection
2Measurement precision
If the threshold value is made optionally changeable by the driver, then detection accuracy can be improved through personalization, but device complexity increases due to additional confirmation functions
Solution Approach 1:
The system automatically performs baseline measurement and threshold setting without requiring driver intervention or manual configuration. The driver simply needs to provide baseline data during a preliminary period, after which the system autonomously adjusts thresholds, maintaining high detection accuracy while minimizing complexity
Solution Approach 2:
The system collects baseline PERCLOS data during an initial period before actual detection begins. This preliminary data collection enables automatic threshold calibration without requiring the driver to manually adjust settings or review historical data, thus improving accuracy while keeping the interface simple
3Measurement precision
If the driver must confirm past PERCLOS history and threshold value to change settings, then personalization is possible, but ease of operation deteriorates due to annoying confirmation requirements
Solution Approach 1:
The system automatically uses the driver's own baseline PERCLOS data to set personalized thresholds without requiring the driver to review or confirm historical data. The personalization happens autonomously in the background, maintaining both accuracy and ease of operation
Solution Approach 2:
The system performs all necessary data collection and threshold calculation during an initial baseline period before actual detection begins. Once established, these personalized settings work automatically without requiring driver confirmation or interaction during normal operation, thus achieving personalization without operational burden
Data Source
AI summary
A drowsiness detection device includes, an imaging unit, a PERCLOS calculation unit, a drowsiness detection unit, and a threshold value setting unit. The PERCLOS calculation unit calculates, based on an image imaged by a camera, a PERCLOS that is a time period ratio during which a driver closes the eye within a certain time period. The drowsiness detection unit detects drowsiness of the driver when the PERCLOS is equal to or larger than a threshold value. When an initial PERCLOS first calculated from a start of driving is less than a %, the threshold value setting unit sets the threshold value to be smaller than in a case that the initial PERCLOS is equal to or larger than a %.