Stereo based 3D head pose tracking using the scale invariant featrue transform

In this paper a new stereo-based 3D head tracking technique, based on scale-invariant feature transform (SIFT) features is proposed. A 3D head tracker is very important preprocessing for many vision applications. The proposed method is robust to out of plane rotations and translations and also invariant to sudden changes in time varying illumination. We present experiments to test the accuracy of our SIFT based 3D tracker on sequences of synthetic and real stereo images.