Main purpose of this paper is to study facial feature based human head position detection. The facial feature extraction methods suitable for a real-time system are considered. Based on the literature survey, an experimental head tracking and pose estimation system is implemented in this paper. An efficient method based on skin detection model, gray-scale morphology and a geometrical face model are applied to detect roughly the face region such as eyes and nose in this project and extract facial features such as eyes point and nose tip. The system automatically initializes whenever the face of a driver is detected. After successful face detection, the tracker is started. The extended three point algorithm is utilized for tracking and estimation of the 3-D pose of the moving head in an image sequence. During tracking the correspondences between a rigid head model and three extracted facial features (eyes and nose) are used to solve the pose.
Loading....