Topological Methods for Motion Data Analysis

We present a new method for analyzing imagebased motion data with topological methods for flow fields. A video sensor captures motion of subjects and yields discrete samples of velocity vectors in the image domain. We show how to construct a smooth, continuous, globally defined bidirectional flow field which evaluates determined vectors at given samples. We then apply a topological analysis of this continuous flow field which yields a segmentation into regions of similar flow behavior, i.e., regions of similar motion.