A simple 3D face tracking method based on depth information

3D face tracking is useful in many applications such as face recognition, analysis of facial expressions and entertainment. Most existing 3D face tracking methods employ multiple cameras and all cameras need to be calibrated first before tracking. The complexity of these methods restricts the applications of them. This paper presents a new simple face tracking method which is based on a stereo vision camera system. All cameras in this stereo vision camera system are pre-calibrated and the system can provide accurate depth information of the scene. The proposed tracking method adopts KLT and template matching to track 2D facial features. Then the stereo vision camera system is used to obtain corresponding depth information of these features. In order to achieve robust tracking, some spatial constraints of these features are employed. Experiment results indicate that the proposed method can achieve robust and accurate 3D face tracking.