ML Anthology

Using Particles to Track Varying Numbers of Interacting People

Kevin Smith, Daniel Gatica-Perez, Jean-Marc Odobez
CVPR 2005 pp. 962-969
doi:10.1109/CVPR.2005.361 /cvpr/2005/smith2005cvpr-using/

Abstract

In this paper, we present a Bayesian framework for the fully automatic tracking of a variable number of interacting targets using a fixed camera. This framework uses a joint multi-object state-space formulation and a trans-dimensional Markov Chain Monte Carlo (MCMC) particle filter to recursively estimates the multi-object configuration and efficiently search the state-space. We also define a global observation model comprised of color and binary measurements capable of discriminating between different numbers of objects in the scene. We present results which show that our method is capable of tracking varying numbers of people through several challenging real-world tracking situations such as full/partial occlusion and entering/leaving the scene.

CVPR Semantic Scholar

Cite

Text

Smith et al. "Using Particles to Track Varying Numbers of Interacting People." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.361

Markdown

[Smith et al. "Using Particles to Track Varying Numbers of Interacting People." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/smith2005cvpr-using/) doi:10.1109/CVPR.2005.361

BibTeX

@inproceedings{smith2005cvpr-using,
  title     = {{Using Particles to Track Varying Numbers of Interacting People}},
  author    = {Smith, Kevin and Gatica-Perez, Daniel and Odobez, Jean-Marc},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {962-969},
  doi       = {10.1109/CVPR.2005.361},
  url       = {https://mlanthology.org/cvpr/2005/smith2005cvpr-using/}
}