The Visual Computer

, Volume 24, Issue 4, pp 271–280

Enriching a motion database by analogous combination of partial human motions

  • Won-Seob Jang
  • Won-Kyu Lee
  • In-Kwon Lee
  • Jehee Lee
Original Article

DOI: 10.1007/s00371-007-0200-1

Cite this article as:
Jang, WS., Lee, WK., Lee, IK. et al. Visual Comput (2008) 24: 271. doi:10.1007/s00371-007-0200-1

Abstract

We have synthesized new human body motions from existing motion data, by dividing the body of an animated character into several parts, such as upper and lower body, and partitioning 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 and dynamic balance.

Keywords

Character animation Motion synthesis 

Copyright information

© Springer-Verlag 2007

Authors and Affiliations

  • Won-Seob Jang
    • 1
  • Won-Kyu Lee
    • 1
  • In-Kwon Lee
    • 1
  • Jehee Lee
    • 2
  1. 1.Dept. of Computer ScienceYonsei UniversitySeoulKorea
  2. 2.School of Computer Science and EngineeringSeoul National UniversitySeoulKorea

Personalised recommendations