Human Motion Retrieval with Symbolic Aggregate approXimation

Motion capture data exhibits its complexity both spatially and temporally, which makes it a hard work to measure the similarities between human motions. We propose a motion data indexing and retrieval method based on self-organizing map and symbolic aggregate approximation. And the hierarchical clustering method is implemented, which can discover the relationships between different motion types by a binary tree structure. Then the motion motifs of each cluster are extracted for the retrieval of example-based query. The experiment results show the performance of our approach.