Implementation of Haar Cascade Classifier and Eye Aspect Ratio for Driver Drowsiness Detection Using Raspberry Pi

TLDR: The findings revealed that the accuracy of Haar Cascade classifier to detect the eyes and faces was subjected to correct sitting position as well as the eyes must not be covered with glasses or shades, and the range of average EAR value detected by the system was between 0.141 and 0.339.

Abstract: Driver’s drowsiness is one of the leading contributing factors to the increasing accidents statistics in Malaysia. Therefore, the design and development of driver drowsiness detection based on image processing using Raspberry Pi camera module sensor interfacing with Raspberry Pi 3 board are proposed in this paper. To achieve the aim of the research, the Haar Cascade Classifier algorithm is implemented for eyes and face detection whereas for eyes blink (open and close) detection, the Eye Aspect Ratio (EAR) algorithm is employed. From several experiments conducted on six recruited subjects, the findings revealed that the accuracy of Haar Cascade classifier to detect the eyes and faces was subjected to correct sitting position (head must facing to the camera) as well as the eyes must not be covered with glasses or shades. Meanwhile, the range of average EAR value detected by the system was between 0.141 (eyes closed) and 0.339 (eyes opened). In conclusion, the image processing-based Haar Cascade and EAR algorithms utilized on Raspberry Pi platform have been successfully executed. For future improvement, the current board can be replaced with Raspberry Pi Touch Screen to minimize the hardware setup and the physiological based analysis using alcohol and heart rate sensors can be added.