Hierarchical visual motion retrieval system and its motion features

This paper proposes a hierarchical visual motion retrieval system on the web. To make it possible for the user to retrieve motion data interactively and visually on a computer screen from coarse level to fine level about motion similarity, the proposed system employs tree based visualization method for the hierarchical structure of motion data. The hierarchical structure of motion data is constructed by recursively applying k-means clustering to them. For applying k-means clustering to motion data, their similarity features should be extracted from them. In this paper, the authors also propose such motion features based on the space division quantization method and position/speed information of motions. The paper clarifies the availability of the proposed features as similarity measure among motions by quantitative evaluations using an actual motion database.