ML Anthology

A Nonparametric Bayesian Approach for Enhanced Pedestrian Detection and Foreground Segmentation

Tarek Elguebaly, Nizar Bouguila
CVPRW 2011 pp. 21-26
doi:10.1109/CVPRW.2011.5981800 /cvprw/2011/elguebaly2011cvprw-nonparametric/

Abstract

With the continuous improvements in computer vision techniques, automatic low-cost video surveillance is becoming feasible. In the context of automatic surveillance, an important problem is the development of accurate models for foreground segmentation and pedestrians detection in outdoor scenes. In this paper we study an unsupervised algorithm based on infinite generalized Gaussian mixture models, that take into consideration the disadvantage of visible-light images (i.e. sensitivity to variations in illumination and lights) and infrared images (i.e. sensitivity to outdoor climate and temperature changes).

CVPRW Semantic Scholar

Cite

Text

Elguebaly and Bouguila. "A Nonparametric Bayesian Approach for Enhanced Pedestrian Detection and Foreground Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011. doi:10.1109/CVPRW.2011.5981800

Markdown

[Elguebaly and Bouguila. "A Nonparametric Bayesian Approach for Enhanced Pedestrian Detection and Foreground Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011.](https://mlanthology.org/cvprw/2011/elguebaly2011cvprw-nonparametric/) doi:10.1109/CVPRW.2011.5981800

BibTeX

@inproceedings{elguebaly2011cvprw-nonparametric,
  title     = {{A Nonparametric Bayesian Approach for Enhanced Pedestrian Detection and Foreground Segmentation}},
  author    = {Elguebaly, Tarek and Bouguila, Nizar},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2011},
  pages     = {21-26},
  doi       = {10.1109/CVPRW.2011.5981800},
  url       = {https://mlanthology.org/cvprw/2011/elguebaly2011cvprw-nonparametric/}
}