3D Head Pose Estimation from Multiple Distant Views

A method for human head pose estimation in multicamera environments is proposed. The method computes the textured visual hull of the subject and unfolds the texture of the head on a hypothetical sphere around it, whose parameterization is iteratively rotated so that the face eventually occurs on its equator. This gives rise to a spherical image, in which face detection is simplified, because exactly one frontal face is guaranteed to appear in it. In this image, the face center yields two components of pose (yaw, pitch), while the third (roll) is retrieved from the orientation of the major symmetry axis of the face. Face detection applied on the original images reduces the required iterations and anchors tracking drift. The method is demonstrated and evaluated in several data sets, including ones with known ground truth. Experimental results show that the proposed method is accurate and robust to distant imaging, despite the low-resolution appearance of subjects.