Computer Vision System for Driver Fatigue Detection

Prof. M. M. Mukhedkar Department of E&TC Engineering, DYPCOE, DYPCOE, Ambi, Talegaon Pune, India Abstract—One of the leading reasons for traffic accidents is distracted attention of driver. As day by day numbers of vehicles on road are increasing, the proportion of number of accidents is also increasing. Drivers with a low vigilance level suffer from marked decline in their abilities of perception, recognition, and vehicle control and gives critical situations to their own life and the lives of others. This project aims to design a system which can actively monitors driver vigilance level and alert the driver for any insecure driving condition. Methodology for drowsiness detection of driver is based on viola jones algorithm for face and eyes detection. System is developed using video camera, Raspberry Pi hardware, and open source computer vision library (OpenCV) and Microsoft visual studio. This paper presents a real-time non-intrusive driver monitoring system which explores the driver’s facial expression to detect and alert fatigued drivers.