ML Anthology

ARGMode - Activity Recognition Using Graphical Models

Raffay Hamid, Yan Huang, Irfan A. Essa
CVPRW 2003 pp. 38
doi:10.1109/CVPRW.2003.10039 /cvprw/2003/hamid2003cvprw-argmode/

Abstract

This paper presents a new framework for tracking and recognizing complex multi-agent activities using probabilistic tracking coupled with graphical models for recognition. We employ statistical feature based particle filter to robustly track multiple objects in cluttered environments. Both color and shape characteristics are used to differentiate and track different objects so that low level visual information can be reliably extracted for recognition of complex activities. Such extracted spatio-temporal features are then used to build temporal graphical models for characterization of these activities. We demonstrate through examples in different scenarios, the generalizability and robustness of our framework.

CVPRW Semantic Scholar

Cite

Text

Hamid et al. "ARGMode - Activity Recognition Using Graphical Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2003. doi:10.1109/CVPRW.2003.10039

Markdown

[Hamid et al. "ARGMode - Activity Recognition Using Graphical Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2003.](https://mlanthology.org/cvprw/2003/hamid2003cvprw-argmode/) doi:10.1109/CVPRW.2003.10039

BibTeX

@inproceedings{hamid2003cvprw-argmode,
  title     = {{ARGMode - Activity Recognition Using Graphical Models}},
  author    = {Hamid, Raffay and Huang, Yan and Essa, Irfan A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2003},
  pages     = {38},
  doi       = {10.1109/CVPRW.2003.10039},
  url       = {https://mlanthology.org/cvprw/2003/hamid2003cvprw-argmode/}
}