A robust head pose tracking and estimating aprouch for driver assistant system

This paper introduces a head pose estimation method based on Geometric Approach that automatically localizes the facial components for real-time applications specially driver assistant systems (DAS) in automotive engineering, etc. We have used a statistical model to segment face regions in the image. Once a face is detected it locates the facial parts such as eyes and lips. The algorithm starts from the extraction of skin pixels and geometric features and then face poses are tracked in the image sequence. Experimental results show that the proposed features could describe the structure of driver face image successfully, and have a good performance in real scenes. Proposed system is not only useful for automobile safety and security but also can help the severely handicapped people and can be used in Driver Assistant Devices, Collision Prevention Systems and other ITS applications.