A Novel Motion Retrieval Method Based on Revised Matching Algorithm and High Dimensional Index

Abstract

This paper proposes a method to speed up motion retrieval: matching algorithm improvement and motion high-dimensional index. The fast elimination algorithm is used to delete most of motions that are not similar with samplings. Then indexing of high-dimensional feature is done with 3D motion data structure. The experimental results show that our method outperforms the classical motion retrieval method both in speed and accuracy.