Segmenting motion capture data into distinct behaviors. Graphics Interface

Much of the motion capture data used in animations, commercials, and video games is carefully segmented into distinct motions either at the time of capture or by hand after the capture session. As we move toward col-lecting more and longer motion sequences, however, au-tomatic segmentation techniques will become important for processing the results in a reasonable time frame. We have found that straightforward, easy to imple-ment segmentation techniques can be very effective for segmenting motion sequences into distinct behaviors. In this paper, we present three approaches for automatic seg-mentation. The first two approaches are online, meaning that the algorithm traverses the motion from beginning to end, creating the segmentation as it proceeds. The first assigns a cut when the intrinsic dimensionality of a lo-cal model of the motion suddenly increases. The second places a cut when the distribution of poses is observed to change. The third approach is a batch process and seg-ments the sequence where consecutive frames belong to different elements of a Gaussian mixture model. We as-sess these three methods on fourteen motion sequences and compare the performance of the automatic methods to that of transitions selected manually. Key words: human motion, motion capture, motion seg-mentation, PCA