Dynamic Threshold Eye State Recognition for Driver Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing occupant state recognition systems struggle to accurately determine whether an eye is in an open or closed state due to individual differences in eyelid opening and closing, leading to potential misclassification of half-eye states as fully open or closed.
Innovation Solution
An occupant state recognition apparatus that includes an eyelid opening recognition unit, an eye state determination unit, and a threshold value resetting unit, which adjusts the threshold value based on the maximum and minimum eyelid opening values to account for individual differences, and resets the threshold if the eye state remains inconsistent for a predetermined period or number of occurrences, allowing for precise classification of eye states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a fixed threshold value is used to determine eye open/closed states, then the determination process is simple, but individual differences in eyelid opening/closing cause misclassification of half-eye states
Solution Approach 1:
The patent applies dynamics by transitioning from a fixed threshold value to a dynamic threshold that automatically adapts to each driver's individual eyelid characteristics. The system captures multiple images, determines maximum and minimum eyelid opening values, and dynamically adjusts the threshold based on these measured parameters, allowing the determination criteria to move and adapt rather than remain static.
Solution Approach 2:
The patent changes the parameter of the threshold value from a fixed constant to a variable that is adjusted based on measured eyelid opening parameters. By calculating the maximum and minimum eyelid opening values and setting the threshold between these extremes, the system modifies the determination parameter to suit individual drivers, thereby improving measurement precision without significantly complicating the process.
2Measurement precision
If individual-specific threshold values are calculated based on maximum and minimum eyelid opening, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent applies self-service by enabling the system to automatically calibrate itself without external intervention. The apparatus autonomously captures images, determines maximum and minimum eyelid opening values, calculates the appropriate threshold, and applies it for subsequent eye state determinations. This self-calibrating mechanism improves precision while minimizing the need for manual configuration or complex external adjustment systems.
Solution Approach 2:
The patent implements preliminary action by performing threshold calibration before actual eye state monitoring begins. The system captures a series of images during an initial period to determine the driver's specific eyelid characteristics, pre-calculates the maximum and minimum values, and establishes the personalized threshold in advance. This preliminary setup simplifies the subsequent monitoring process while ensuring high measurement precision from the start.
3Adaptability or versatility
If the threshold value is reset based on predetermined period or number of eyelid openings/closings, then adaptability to individual differences improves, but loss of time occurs during calibration period
Solution Approach 1:
The patent applies periodic action by implementing a calibration process that operates during a predetermined period or after a specific number of eyelid openings/closings have been detected. The system periodically captures images, updates the maximum and minimum eyelid opening values, and resets the threshold accordingly. This periodic recalibration ensures continued adaptability to individual drivers while managing the time investment through structured, interval-based operation.
Data Source
AI summary
An occupant state recognition apparatus including an eyelid opening recognition unit configured to recognize an eyelid opening of a driver and maximum and minimum values of the eyelid opening; an eye state determination unit configured to determine that the eye is in an eye open state if the eyelid opening becomes greater than or equal to a preset threshold value, and to determine that the eye is in an eye closed state if the eyelid opening becomes less than the threshold value; and a threshold value resetting unit configured to reset the threshold value to a value between the maximum value and the minimum value of the eyelid opening, if the maximum value (or the minimum value) has not become greater (or less) than or equal to the threshold value for a predetermined period or a period corresponding to a predetermined number of times of eyelid opening and closing.