A Fast Algorithm Face Detection and Head Pose Estimation for Driver Assistant System

In this paper, a fast algorithm of face detection and head pose estimation is proposed to estimate the head pose for driver surveillance real time. Firstly, faces are accurately detected based on mask transform and SVMs classifier. Subsequently, the face of every frame is tracked in the range of little position and scale. Head pose is estimated on the basis of accurate face detection. At last, we analyzed the head pose by a kind of bilateral-projection matrix principle component analysis (BMPCA) algorithm proposed. Experimental results on many videos show that the algorithm can detect driver´s face rapidly and estimate the head pose accurately