Fatigue detection based on the distance of eyelid

A vision-based real-time driver fatigue detection method is proposed in this paper. Firstly, The face is located using the characteristics of skin colors, then the eyes are detected by projections and finding connected components and is used as the dynamic templates for eye tracking in the following frame. Finally, it can decide whether the driver is fatigue by detecting the distance change of the eyelid. The average correct rate for eye location and tracking can reach 98%, the correct rate for fatigue detection is 100%, the average precision rate is 90%.