Real-Time Optimization for the High-Fidelity of Human Motion Imitation

Abstract

This paper proposes a real-time optimization method for the high-fidelity of human motion imitation using a marker-based motion capture system. Although many ways to generate realistic synthetic motions from the capturing data have been developed, there are common problems related to marker occlusion. Our approach is useful for getting over marker occlusion in real-time system environments, and this is fit for altering human motion to other skeleton structures such as human avatars and humanoid robots. In this paper, we applied the proposed optimization method to construct the whole body joint configuration. The result has been demonstrated by simulation test using a 20-DOF skeleton model.