Drowsiness Detection Using Multiple Blinking Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing drowsiness determination systems face issues in accurately extracting blinking feature amounts due to inappropriate threshold values, leading to incorrect extraction of drowsiness states caused by noise or variations near the closed-eye threshold value.
Innovation Solution
A drowsiness determination apparatus and program that employ multiple threshold values for different types of blinking feature amounts, including those related to blinking grouping, number of blinks, and duration of open- and closed-eye states, to accurately determine drowsiness with precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single standard threshold value is used for extracting blinking feature amounts, then the device complexity is reduced, but the measurement precision of drowsiness determination deteriorates due to noise and variations near the threshold value
Solution Approach 1:
The patent segments the single threshold value into multiple threshold values (first threshold value and second threshold value) that differ by a predetermined offset. This segmentation allows different threshold values to be used for different blinking feature amount extractions, improving measurement precision while maintaining manageable device complexity through systematic organization of the multiple thresholds.
Solution Approach 2:
The patent changes the threshold value parameter by introducing a predetermined offset between the first and second threshold values. This parameter change enables the system to extract different blinking feature amounts using slightly different threshold criteria, thereby improving measurement precision without significantly increasing device complexity.
2Measurement precision
If a higher threshold value is used to avoid noise-induced incorrect extraction, then the measurement precision improves, but the reliability of detecting sustained closed-eye states deteriorates
Solution Approach 1:
The patent segments the threshold value usage into two distinct threshold values: a first threshold value for extracting certain blinking feature amounts and a second threshold value (offset from the first) for extracting other blinking feature amounts. This segmentation allows the system to maintain high measurement precision for individual feature extractions while ensuring reliable drowsiness state determination through complementary threshold pairs.
Solution Approach 2:
The patent introduces a predetermined offset as a parameter change between the first and second threshold values. This controlled parameter change enables the system to balance measurement precision and reliability by using slightly different threshold criteria for different aspects of blinking analysis, ensuring that noise-induced errors are minimized while sustained closed-eye states are reliably detected.
3Measurement precision
If multiple threshold values are employed for different blinking feature amounts, then the measurement precision of drowsiness determination improves, but the device complexity increases
Solution Approach 1:
The patent segments the threshold value management into two distinct but related threshold values with a predetermined offset relationship. This segmentation improves measurement precision by allowing specialized threshold values for different blinking feature amounts, while the systematic offset relationship keeps the complexity manageable through organized structure.
Solution Approach 2:
The patent employs a predetermined offset as a controlled parameter change between threshold values. This approach improves measurement precision by enabling nuanced threshold differentiation while minimizing device complexity through a simple, systematic parameter relationship that is easy to implement and manage.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An image is captured of a region including an eye of a driver using an image capture device 12, and the degree of eye openness is detected with a degree of eye openness detection section 24. A standard closed eye threshold value, a large value closed eye threshold value and a small closed eye threshold value stored in the threshold value storage section 28 are employed by the feature amount extraction section 30 to extract plural types of blinking feature amount from the detected degree of eye openness time series data. Threshold value determination is performed for each of the plural types of blinking feature amount by the threshold value determination section 32, and determination of the state of drowsiness of the driver is made by the drowsiness determination section 34 based on the threshold value determination results for the plural types of blinking feature amount. Accordingly, respective threshold values appropriate to the types of blinking feature amounts are employed in extracting blinking feature amounts, enabling determination of state of drowsiness to be performed with good precision.