Acquisition of Kinematic Structure of Articulated Rigid Bodies from Time Series Volume Data

This paper presents a new scheme for acquiring 3D kinematic structure and motion from time series volume data. Our basic strategy is to first represent the shape structure of the target in each frame by pseudo Endoskeleton Reeb Graph (pERG) which we compute by using geodesic distance between vertices on the target's surface, and then estimate the kinematic structure of the target that is consistent with these shape structures. Although the shape structures can be very different from frame to frame, we propose to derive a unique kinematic structure by way of clustering nodes of a graph, based on the fact that they are partly coherent to a certain extent of time series. The only assumption we make is that the human body can be approximated by an articulated body with certain numbers of end-points and branches. We demonstrate the efficacy and the limitation of the proposed scheme through experiments.