ML Anthology

Layered Representation for Pedestrian Detection and Tracking in Infrared Imagery

Congxia Dai, Yunfei Zheng, Xin Li
CVPR 2005 pp. 13
doi:10.1109/CVPR.2005.483 /cvpr/2005/dai2005cvpr-layered/

Abstract

This paper introduces a layered representation for infrared imagery and studies its application into pedestrian detection and tracking. We present a generalized EM algorithm to decompose infrared images into background and foreground layers and study the phenomenon of polarity switch. We propose a hybrid (shape+appearance) algorithm for pedestrian detection, in which shape cue is first used to eliminate non-pedestrian moving objects and appearance cue is then used to pin down the location of pedestrians. We also formulate the problem of shot segmentation and present a graph matching-based pedestrian tracking algorithm. Experimental results with OSU Thermal Pedestrian Database are reported to demonstrate the excellent performance of our algorithms.

CVPR Semantic Scholar

Cite

Text

Dai et al. "Layered Representation for Pedestrian Detection and Tracking in Infrared Imagery." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.483

Markdown

[Dai et al. "Layered Representation for Pedestrian Detection and Tracking in Infrared Imagery." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/dai2005cvpr-layered/) doi:10.1109/CVPR.2005.483

BibTeX

@inproceedings{dai2005cvpr-layered,
  title     = {{Layered Representation for Pedestrian Detection and Tracking in Infrared Imagery}},
  author    = {Dai, Congxia and Zheng, Yunfei and Li, Xin},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {13},
  doi       = {10.1109/CVPR.2005.483},
  url       = {https://mlanthology.org/cvpr/2005/dai2005cvpr-layered/}
}