|
Abstract:
Humans demonstrate a remarkable ability to parse complicated motion sequences into their constituent structures and motions. We investigate this problem, attempting to learn the structure of one or more articulated objects, given a time-series of feature positions. We model the observed sequence in terms of ``stick figure'' objects, under the assumption that the relative joint angles between sticks can change over time, but their lengths and connectivities are fixed. We formulate the problem in a single probabilistic model that includes multiple sub-components of the problem: associating the features with particular sticks, determining the proper number of sticks, and finding which sticks are physically joined. We test the algorithm on challenging 2D and 3D datasets: synthetic structures including cycles; optical human motion capture; and video of walking giraffes.