Real Time Eye Detection Algorithm for PERCLOS Calculation

Abstract

The traffic accidents is one of the important problems in our lives. The majority of traffic accidents are caused by inattentive or fatigue which is mostly related to drowsiness. An embedded and contactless system should be designed to deal with this problem in real world conditions. PERCLOS, is the most effective method for drowsiness detection, analyzes drowsiness level of the driver by using eye states. In this study, real time eye detection under infrared illumination algorithm is developed for PERCLOS calculation. The performance evaluation of the presented algorithm is realized with an image database.