Efficient human motion retrieval in large databases

This paper provides methods for identifying visually and numerically similar motions in large motion capture databases given a query of motion segment. Large human motion databases contain variants of natural motions that are valuable for animation generation and synthesis. But retrieving visually similar motions is still a difficult and time-consuming problem. We propose an efficient geometric feature based indexing strategy that represents the motions compactly through apreprocessing. This representation scales down the range of searching the database. Motions in this range are possible candidates of the final matches. For detailed comparisons between the query and the candidates, we propose an algorithm that compares the motions' curves using an efficient motion curve matching algorithm. Our methods can apply to large human motion databases and achieve high performance and accuracy compared with previous work.