A single camera motion capture system dedicated to gestures imitation

Paulo Menezes, Frédéric Lerasle, Jorge Dias, Raja Chatila

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

8 Scopus citations

Abstract

This article describes a method to track 3D articulated structures from a monocular perspective image sequence using a particle filter. This structure is composed of a set of linked degenerated quadrics (cones) which are truncated by pairs of planes also modelled as degenerated quadrics. This set of truncated cones is connected by joints containing one or more degrees of freedom. The method is based upon the estimation of the contours of the structure's silhouette projected on the image plane, to validate each of the particles which correspond to proposed configurations. This validation is performed using a criterion that combines a measure based on the contours, a measure of similarity between the colour distribution around a point on the structure and a reference distribution, and other criteria that reinforce the overall cost function. The results show the feasibility of the approach when using a single camera to track a 3D model containing eight degrees of freedom.

Original languageBritish English
Title of host publicationProceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots
Pages430-435
Number of pages6
DOIs
StatePublished - 2005
Event2005 5th IEEE-RAS International Conference on Humanoid Robots - Tsukuba, Japan
Duration: 5 Dec 20057 Dec 2005

Publication series

NameProceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots
Volume2005

Conference

Conference2005 5th IEEE-RAS International Conference on Humanoid Robots
Country/TerritoryJapan
CityTsukuba
Period5/12/057/12/05

Keywords

  • 3D tracking
  • Articulated structures
  • Gesture imitation
  • Monocular vision
  • Particle filters

Fingerprint

Dive into the research topics of 'A single camera motion capture system dedicated to gestures imitation'. Together they form a unique fingerprint.

Cite this