Automatic Subspace Synthesis of Motion Styles Based on Isomap

  • Authors:
  • Jian Xiang;Hongli Zhu

  • Affiliations:
  • School of Information and Electronic Engineering, ZheJiang, University of Science and Technology, HangZhou, China 310023;College of Information & Electrical Engineering, ZheJiang University City College, HangZhou, China 310015

  • Venue:
  • ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Artificial Intelligence
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Motion synthesis methods based on 3D motion data are extensively studied in recent years. And 3D motion styles synthesis has been rarely explored. In this paper, a method for automatic and quantitative synthesis human motion styles is proposed. First extended ISOMAP theory is used to map original motions into low-dimensionality subspaces, which can reserve the intrinsic properties of original data. Synthesis is applied in such new subspaces and motion styles can be reconstructed. Experimental results show that our methods are effective.