Perceiving Systems, Computer Vision

A framework for modeling the appearance of 3D articulated figures

2000

Conference Paper

ps


This paper describes a framework for constructing a linear subspace model of image appearance for complex articulated 3D figures such as humans and other animals. A commercial motion capture system provides 3D data that is aligned with images of subjects performing various activities. Portions of a limb’s image appearance are seen from multiple views and for multiple subjects. From these partial views, weighted principal component analysis is used to construct a linear subspace representation of the “unwrapped” image appearance of each limb. The linear subspaces provide a generative model of the object appearance that is exploited in a Bayesian particle filtering tracking system. Results of tracking single limbs and walking humans are presented.

Author(s): Sidenbladh, H. and De la Torre, F. and Black, M. J.
Book Title: Int. Conf. on Automatic Face and Gesture Recognition
Pages: 368-375
Year: 2000
Month: March

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Address: Grenoble, France

Links: pdf

BibTex

@inproceedings{Black:ICAFGR:2000,
  title = {A framework for modeling the appearance of {3D} articulated figures},
  author = {Sidenbladh, H. and De la Torre, F. and Black, M. J.},
  booktitle = {Int. Conf. on Automatic Face and Gesture Recognition},
  pages = {368-375},
  address = {Grenoble, France},
  month = mar,
  year = {2000},
  doi = {},
  month_numeric = {3}
}