Virtual Human Motion Extension Based on Bayesian Network

Abstract

Aiming at the problem of virtual human motion reuse, the concept of motion extension is proposed, which includes lengthways extension and transverse extension. The lengthways extension extends motion along the time, and generates more frames from existing motion. The transverse extension extends motion to other characters, and multiple characters motion is generated by single character motion. Each motion in the group is similar and different from each other. Motion extension provides unified solution to important issues such as motion prediction, motion repair, and group motion. We construct the Bayesian network of the virtual human motion, which studies and reduces the dimension of the virtual human motion, and propose a method of motion extension based on Bayesian network. Experiments show that our method can generate more realistic virtual human motion based on existing motion, and provide support for the application of virtual human in the fields of bio-engineering, medicine and military.