Real Time Eyes Tracking and Classification for Driver Fatigue Detection

* Final gross prices may vary according to local VAT.

Get Access


In this paper, we propose a vision-based real time algorithm for driver fatigue detection. Face and eyes of the driver are first localized and then marked in every frame obtained from the video source. The eyes are tracked in real time using correlation function with an automatically generated online template. The proposed algorithm can detect eyelids movement and can classify whether the eyes are open or closed by using normalized cross correlation function based classifier. If the eyes are closed for more than a specified time an alarm is generated. The accuracy of algorithm is demonstrated using real data under varying conditions for people with different gender, skin colors, eye shapes and facial hairs.