A New Real-Time Eye Tracking for Driver Fatigue Detection

Driver fatigue is one of the important factors that cause traffic accidents. The vision-based facial expression recognition technique is the most prospective method to detect driver fatigue. In this paper, we present a new driver fatigue detection based on unscented Kalman filter and eye tracking in this paper. The face is located using Haar algorithm firstly, which has good robustness in terms of head motions, variable lighting conditions, the change of hair and having glasses, etc. Secondly, the geometric properties and projection technique are used for eye location. Thirdly, we propose a new real time eye tracking method based on unscented Kalman Filter. Finally, driver fatigue can be detected whether the eyes are closed over 5 consecutive frames using vertical projection matching. The experimental results show validity of our method for driver fatigue detection under variable realistic conditions