Driver Drowsiness Detection System with OpenCV and Keras
4 Pages Posted: 20 Jul 2021
Date Written: July 12, 2021
Abstract
Several studies have reported indicating that driver drowsiness has caused multiple number of accidents over the past years. So, in an effort to prevent such accidents, measures are to be implemented. One such measure is a Driver Drowsiness Detection software; the software will set off an alarm once the driver keeps his/her eyes closed for a certain amount of time. This paper proposes to detect whether the driver is sleepy or not by using OpenCV with eyelid related parameters. The data consists of around 9723 images of eyes under different optical conditions. The used dataset is divided into three parts for the sake of convenience i.e. frontal face detection, left eye detection and right eye detection. With all the features, an OpenCV and keras a driver’s fatigue or drowsiness model is built. The validation results indicate the precision and accuracy of the proposed model.
Suggested Citation: Suggested Citation