Human Motion Segmentation Algorithm: Manifold Learning of Sequence Local Warp

Most of segmentation methods based on manifold learning utilize globally or locally linear strategies.However, these linear strategies can not cope with the high curvature structure of sequence dataset.Considering the continuity of human motion and the local high curvature in human motion sequence, a segmentation method using manifold learning is proposed to deal with the segmentation problem in this paper.The method evaluates the coherence of human motion based on the local warp index of sequence data.As the transition clips between the certain adjacent motion units warp largely, the filtering technique as well as the piecewise linear representation is applied to deal with the motion sequence.The experimental results show that the proposed method combined with the characteristic curves of the dimensionality reduction is effective to the segmentation of the CMU human motion datasets etc..