ML Anthology

A Modular Approach to the Analysis and Evaluation of Particle Filters for Figure Tracking

Ping Wang, James M. Rehg
CVPR 2006 pp. 790-797
doi:10.1109/CVPR.2006.32 /cvpr/2006/wang2006cvpr-modular/

Abstract

This paper presents the first systematic empirical study of the particle filter (PF) algorithms for human figure tracking in video. Our analysis and evaluation follows a modular approach which is based upon the underlying statistical principles and computational concerns that govern the performance of PF algorithms. Based on our analysis, we propose a novel PF algorithm for figure tracking with superior performance called the Optimized Unscented PF. We examine the role of edge and template features, introduce computationally-equivalent sample sets, and describe a method for the automatic acquisition of reference data using standard motion capture hardware. The software and test data are made publicly-available on our project website.

CVPR Semantic Scholar

Cite

Text

Wang and Rehg. "A Modular Approach to the Analysis and Evaluation of Particle Filters for Figure Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.32

Markdown

[Wang and Rehg. "A Modular Approach to the Analysis and Evaluation of Particle Filters for Figure Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/wang2006cvpr-modular/) doi:10.1109/CVPR.2006.32

BibTeX

@inproceedings{wang2006cvpr-modular,
  title     = {{A Modular Approach to the Analysis and Evaluation of Particle Filters for Figure Tracking}},
  author    = {Wang, Ping and Rehg, James M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {790-797},
  doi       = {10.1109/CVPR.2006.32},
  url       = {https://mlanthology.org/cvpr/2006/wang2006cvpr-modular/}
}