Automatically Mapping Human Skeletons onto Virtual Character Armatures

Abstract

Motion capture systems provide an efficient and interactive solution for extracting information related to a human skeleton, which is often exploited to animate virtual characters. When the character cannot be assimilated to an anthropometric shape, the task to map motion capture data onto the armature to be animated could be extremely challenging. This paper presents a novel methodology for the automatic mapping of a human skeleton onto virtual character armatures. By extending the concept of graph similarity, joints and bones of the tracked human skeleton are mapped onto an arbitrary shaped armature. A prototype implementation has been developed by using the Microsoft Kinect as body tracking device. Preliminary results show that the proposed solution can already be used to animate truly different characters such as a Pixar-like lamp, a fish or a dog.