Collaborated Directional Chamfer Matching for 3D Hand Pose Estimation

We describe a shape-based chamfer matching method for recovering 3D hand pose using a monocular camera. Although some variants of chamfer matching methods incorporated edge direction information, of which the direction term is set empirically, so they may fail in different application scenario. In this paper, a collaborated directional chamfer matching (CDCM) is proposed. The direction term can be directly converted to a distance term, so a normalization factor is no more needed, and the similarity measurement can be directly calculated in scale space without adjusting the normalization factor. At the same time, a two layered structure is constructed using both the Active shape models (ASM) and the proposed CDCM to get the precise pose. Experimental results show the effectiveness of the proposed method.