Subspace Index Method for 3D Human Motion

Along with the development of motion capture technique, more and more large-scale 3D motion databases become available. In this paper, a novel approach is presented for motion retrieval based on a novel index method. Due to high dimensionality of Motion's features, the dimension reduction is used. Then an index system is built based on s the low-dimensional subspace tree. So we can reduce the number of costly similarity measure significantly. Experiment results show that the approaches are effective for motion data retrieval in large-scale databases.