A Method of Hyper-sphere Cover in Multidimensional Space for Human Mocap Data Retrieval

Abstract

A method of hyper-sphere cover in multidimensional space for human Mocap (Motion Capture) data retrieval is presented in this paper. After normalization and feature extraction, both the retrieval instance and the motion data are mapping into a multidimensional space. Several hyper-spheres are constructed according to the retrieval instance, and the domain covered by these hyper-spheres can be considered as the distribution range of a same kind of motions. By use of CMU free motion database, the retrieval algorithm has been implemented and examined and the experimental results are illustrated. At the same time, the main contributions and limitations are discussed.