Vision based approach for driver drowsiness detection based on 3D head orientation

Abstract

The increasing number of accidents is attributed to several factors, among which is the lack of concentration caused by fatigue. The driver drowsiness state can be detected with several ways. Among these methods, we can quote those which analyze the driver eyes or head by video or studying the EEG signal. We present, in this paper an approach which makes it possible to determine the orientation of the driver head to capture the drowsiness state. This approach is based on the estimation of head rotation angles in the three directions yaw, pitch and roll by exploiting only three points face features. © 2013 Springer Science+Business Media Dordrecht(Outside the USA).