A Efficient Method for Motion Retrieval Based on Mocap Database

In this paper, a novel approach is presented for motion retrieval based on double-reference inde(DRI) in motion capture(mocap) database. Due to high dimensionality of motion´s feature, first 3D temporal-spatial features and their keyspaces of each human joint are extracted. Then DRI is build based on selecting a small set of representative motion clips in the database by these features. So we can get candidate set by abandoning most unrelated motion clips to reduce the number of costly similarity measure significantly. Experimental results show that our methods are effective for motion data retrieval in large database.