Abstract
Drowsy driving and drink driving are two of the major causes of serious traffic accidents, which arouse an area of great socioeconomic concern. Continuous monitoring of drivers’ state thus is of great importance to reduce drowsy and drunken caused accidents. An early warning system was proposed for real-time driver state monitoring. The system not only eliminates drink driving by sensor technique, but also uses a computer vision system to track the eyes for drowsiness detection of drivers. The experimental results of this system showed exceed 88.3% eye detection rate which verified the practicability of the system. (Author/publisher)