Enriching a motion database by analogous combination of partial human motions

We synthesize new human body motions from existing motion data. We divide the body of an animated character into several parts, such as to upper and lower body, and partition the motion of the character into corresponding partial motions. By combining different partial motions we can generate new motion sequences. We select the most natural-looking combinations by analyzing the similarity of partial motions using techniques such as motion segmentation, dimensionality reduction, and clustering. These new combinations can dramatically increase the size of a motion database, allowing more score in selecting motions to meet constraints such as collision avoidance. We verify the naturalness and physical plausibility of the new motions using an SVM learning model and by analysis of static balance. Keywords Character animation

• Type: Journal
• Year: 2008
• Where: VC
• Authors: Won-Seob Jang, Won-Kyu Lee, In-Kwon Lee, Jehee Lee
• Keywords: Human Body Motions, Motion Data, Partial Motions, VC 2008