Abstract
To provide efficient tools for the capture and modeling of acceptable virtual human poses, we propose a method for constraining the underlying joint structures based on real life data. Current tools for delimiting valid postures often employ techniques that do not represent joint limits in an intuitively satisfying manner, and furthermore are seldom directly derived from experimental data. Here, we propose a semi-automatic scheme for determining ball-and-socket joint limits by actual measurement and we apply it to modeling the shoulder complex, which—along with the hip complex—can be approximated by a three-degree-of-freedom ball-and-socket joint. Our first step is to measure the joint motion range using optical motion capture. We next convert the recorded values to joint poses encoded using a coherent quaternion field representation of the joint orientation space. Finally, we obtain a closed, continuous implicit surface approximation for the quaternion orientation-space boundary whose interior represents the complete space of valid orientations, enabling us to project invalid postures to the closest valid ones.