Robust 3D head tracking by online feature registration
Jun-Su Jang, Takeo Kanade · 2008
This paper presents a robust method for tracking the position and orientation of a head in videos. The proposed method can overcome occlusions and divergence problems. We introduce an online registration technique to detect and register feature point of the head while tracking. A set of point features is registered and updated for each reference pose serving a multi-view head detector. The online feature registration rectifies error accumulation and provides fast recovery after occlusion has ended, while preventing divergence problem which frequently occurs in conventional frame-to-frame tracking methods. The robustness of the proposed tracker is experimentally shown with video sequences that include occlusions and large pose variations. 1.