Acquisition of Articulated Human Body Models Using Multiple Cameras

Abstract

Motion capture is an important application in different areas such as biomechanics, computer animation, and human-computer interaction. Current motion capture methods typically use human body models in order to guide pose estimation and tracking. We model the human body as a set of tapered super-quadrics connected in an articulated structure and propose an algorithm to automatically estimate the parameters of the model using video sequences obtained from multiple calibrated cameras. Our method is based on the fact that the human body is constructed of several articulated chains that can be visualised as essentially 1-D segments embedded in 3-D space and connected at specific joint locations. The proposed method first computes a voxel representation from the images and maps the voxels to a high dimensional space in order to extract the 1-D structure. A bottom-up approach is then suggested in order to build a parametric (spline-based) representation of a general articulated body in the high dimensional space followed by a top-down probabilistic approach that registers the segments to the known human body model. We then present an algorithm to estimate the parameters of our model using the segmented and registered voxels.