Computer Vision based Driver Drowsiness Detection System

Nowadays, The main reason for most of the accidents is driver drowsiness in the most of countries. Detecting the driver yawning and eye tiredness is the easiest way for measuring the drowsiness of driver. The existing systems in the literature survey, are providing slightly less accurate results due to low clarity in images and videos, sensor problems hardware problem. In order to solve this problem, a driver drowsiness detection system is proposed in this paper, which makes use of eye blink counts and yawn counts for detecting the drowsiness. The proposed framework continuously analyzes the eye and mouth movement of the driver and alerts the driver by sounding the alarm when he/she is drowsy. An alarm will be generated to warn the driver when the eyes are detected closed for too long time,. The proposed system is implemented on Python and uses OpenCV library, with a single camera view (Raspberry Pi/Webcam). It provides good performance by accurate drowsiness detection results and thereby reduces the road accidents.