Drowsiness Detection – A Visual System for Driver Support

Driving is a complex task that requires constant attention from all senses. Vision based Driver Assistance System in comprise of various sub systems like lane departing warning, traffic sign recognition, intelligent head lamp control, pedestrian detection etc. This paper demonstrates a work towards safety system especially for fatigue car drivers so as to prevent accidents. The system uses a small monochrome camera that points directly towards the driver’s face and monitors the driver’s eyes in order to detect fatigue. In such a case when fatigue is detected, a warning signal is issued to alert the driver. This paper describes the procedure to detect eyes, and also to determine if the eyes are open or closed. The proposed system uses information obtained form of the image to find the edges of the face, and finds the possibility of area of eyes. Once edge detection has been done, the eyes are found by using Circular Hough Transform. Taking into account the knowledge that number of circles found for every image, we decide whether eyes are closed or opened. An absence of circles corresponds to eye closure. If the eyes are found closed for 8 consecutive frames, the system draws the conclusion that the driver is falling asleep and issues a warning signal. The system works under reasonable lighting conditions.