Share Email Print

Optical Engineering • Open Access

Automatic human body modeling for vision-based motion capture system using B-spline parameterization of the silhouette
Author(s): Antoni Jaume-i-Capo; Javier Varona; Manuel Gonzalez-Hidalgo; Ramon Mas; Francisco J. Perales

Paper Abstract

Human motion capture has a wide variety of applications, and in vision-based motion capture systems a major issue is the human body model and its initialization. We present a computer vision algorithm for building a human body model skeleton in an automatic way. The algorithm is based on the analysis of the human shape. We decompose the body into its main parts by computing the curvature of a B-spline parameterization of the human contour. This algorithm has been applied in a context where the user is standing in front of a camera stereo pair. The process is completed after the user assumes a predefined initial posture so as to identify the main joints and construct the human model. Using this model, the initialization problem of a vision-based markerless motion capture system of the human body is solved.

Paper Details

Date Published: 7 March 2012
PDF: 4 pages
Opt. Eng. 51(2) 020501 doi: 10.1117/1.OE.51.2.020501
Published in: Optical Engineering Volume 51, Issue 2
Show Author Affiliations
Antoni Jaume-i-Capo, Univ. de les Illes Balears (Spain)
Javier Varona, Univ. de les Illes Balears (Spain)
Manuel Gonzalez-Hidalgo, Univ. de les Illes Balears (Spain)
Ramon Mas, Univ. de les Illes Balears (Spain)
Francisco J. Perales, Univ. de les Illes Balears (Spain)

© SPIE. Terms of Use
Back to Top