Generating human motion along pre-defined path in real-time

Man Lung Lau, Bartholomew Iu, Chapmann Chow, Pouro Lee

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

While many previous works to generate human motion has been proposed, these techniques are offline, memory inefficient and may require past and future time frames during the synthesis process. The objective of this paper is to propose an algorithm for human motion synthesis which targets for real-time applications. This algorithm was originally developed under a crowd simulation project which simulates the motion of the people by using a motion captured data library. Four main features of this synthesis algorithm include generating motion along a given path with the speed matched, adapting the motion to the scaled skeleton, running with an interactive speed and small memory footprint.
Original languageEnglish
Title of host publication5th International Conference on Information Technology and Applications, ICITA 2008
Pages695-700
Number of pages6
Publication statusPublished - 1 Dec 2008
Event5th International Conference on Information Technology and Applications, ICITA 2008 - Cairns, QLD, Australia
Duration: 23 Jun 200826 Jun 2008

Conference

Conference5th International Conference on Information Technology and Applications, ICITA 2008
Country/TerritoryAustralia
CityCairns, QLD
Period23/06/0826/06/08

Keywords

  • Crowd simulation
  • Motion synthesis
  • Online algorithm
  • Real-time application

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems
  • Software

Cite this