Side-Face Drowsiness Detection for Drivers With Glasses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing drowsy driving detection technologies face challenges due to individual differences among drivers, such as those wearing glasses or having eye defects, leading to inaccurate detection and high computational resource consumption.
Innovation Solution
The method uses side face images to detect eye movement features, establishes personalized ID files for each driver, and employs adaptive camera and lighting adjustments to enhance accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a unified standard recognition algorithm is used for all drivers, then the system is simple to implement, but detection accuracy decreases for drivers with special conditions (glasses, eye defects)
Solution Approach 1:
The system changes the detection parameters by switching from frontal face images to side face images. This parameter change allows accurate detection for drivers wearing glasses or with eye defects, as the side view avoids lens interference and captures eye features more reliably, resolving the accuracy issue without requiring complex individualized models for each driver type
Solution Approach 2:
The system segments the detection approach by creating separate processing paths: one for side face image acquisition and another for personalized model matching. This segmentation allows the system to handle individual differences through personalized models while maintaining overall system simplicity through a standardized side-face-based workflow
2Measurement precision
If personalized detection models are created for each driver, then detection accuracy improves, but computational resource consumption increases
Solution Approach 1:
The system performs preliminary action by pre-building personalized detection models for each driver during off-road or idle periods when computational resources are abundant. These models are stored in the system memory, allowing rapid deployment during actual driving without consuming excessive real-time computational resources, thus resolving the contradiction between personalization and resource consumption
3Measurement precision
If frontal face images are used for detection, then the detection process is straightforward, but lens interference from glasses reduces accuracy
Solution Approach 1:
The system applies inversion by completely reversing the conventional approach: instead of using frontal face images as is, it switches to side face images. This inversion eliminates the lens interference problem because the side view captures eye features from an angle that bypasses the glasses lenses, allowing accurate detection without being affected by the harmful factor of lens reflection and distortion
Data Source
AI summary
A drowsy driving detection method comprises: acquiring a side face image of a currently seated driver collected by a camera module; performing face recognition on the side face image to obtain side face feature parameters, and determining, according to the side face feature parameters, whether an ID file corresponding to the currently seated driver exists in a driver ID library; and if yes, periodically acquiring a side face image of the driver in the current period collected by the camera module, obtaining eye movement feature parameters of the driver in the current period according to the side face image of the current period, and determining whether the driver is driving while drowsy according to a comparison result between the eye movement feature parameters of the current period and the normal eye movement feature parameters of the driver.