3D model based gesture acquisition using a single camera

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present a method for 3D human motion capture using a single camera, without markers and without a priori knowledge on gestures. It is based on registering a 3D articulated model on color images with respect to biomechanical constraints. Gestures regularization is discussed as a way to cope with projection ambiguities. Computation is reduced by registering only the moving parts of the body.

Original languageEnglish
Title of host publicationProceedings - 6th IEEE Workshop on Applications of Computer Vision, WACV 2002
PublisherIEEE Computer Society
Pages158-162
Number of pages5
ISBN (Electronic)0769518583
DOIs
Publication statusPublished - 1 Jan 2002
Externally publishedYes
Event6th IEEE Workshop on Applications of Computer Vision, WACV 2002 - Orlando, United States
Duration: 3 Dec 20024 Dec 2002

Publication series

NameProceedings of IEEE Workshop on Applications of Computer Vision
Volume2002-January
ISSN (Print)2158-3978
ISSN (Electronic)2158-3986

Conference

Conference6th IEEE Workshop on Applications of Computer Vision, WACV 2002
Country/TerritoryUnited States
CityOrlando
Period3/12/024/12/02

Keywords

  • Biological system modeling
  • Cameras
  • Color
  • Computer vision
  • Cost function
  • Hidden Markov models
  • Humans
  • Machine vision
  • Solid modeling
  • Weapons

Fingerprint

Dive into the research topics of '3D model based gesture acquisition using a single camera'. Together they form a unique fingerprint.

Cite this