ML Anthology

Information Theoretic Sensor Management for Multi-Target Tracking with a Single Pan-Tilt-Zoom Camera

Pietro Salvagnini, Federico Pernici, Marco Cristani, Giuseppe Lisanti, Iacopo Masi, Alberto Del Bimbo, Vittorio Murino
WACV 2014 pp. 893-900
doi:10.1109/WACV.2014.6836009 /wacv/2014/salvagnini2014wacv-information/

Abstract

Automatic multiple target tracking with pan-tilt-zoom (PTZ) cameras is a hard task, with few approaches in the lit-erature, most of them proposing simplistic scenarios. In this paper, we present a PTZ camera management framework which lies on information theoretic principles: at each time step, the next camera pose (pan, tilt, focal length) is chosen, according to a policy which ensures maximum information gain. The formulation takes into account occlusions, phys-ical extension of targets, realistic pedestrian detectors and the mechanical constraints of the camera. Convincing com-parative results on synthetic data, realistic simulations and the implementation on a real video surveillance camera val-idate the effectiveness of the proposed method. 1.

PDF WACV Semantic Scholar

Cite

Text

Salvagnini et al. "Information Theoretic Sensor Management for Multi-Target Tracking with a Single Pan-Tilt-Zoom Camera." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014. doi:10.1109/WACV.2014.6836009

Markdown

[Salvagnini et al. "Information Theoretic Sensor Management for Multi-Target Tracking with a Single Pan-Tilt-Zoom Camera." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014.](https://mlanthology.org/wacv/2014/salvagnini2014wacv-information/) doi:10.1109/WACV.2014.6836009

BibTeX

@inproceedings{salvagnini2014wacv-information,
  title     = {{Information Theoretic Sensor Management for Multi-Target Tracking with a Single Pan-Tilt-Zoom Camera}},
  author    = {Salvagnini, Pietro and Pernici, Federico and Cristani, Marco and Lisanti, Giuseppe and Masi, Iacopo and Del Bimbo, Alberto and Murino, Vittorio},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2014},
  pages     = {893-900},
  doi       = {10.1109/WACV.2014.6836009},
  url       = {https://mlanthology.org/wacv/2014/salvagnini2014wacv-information/}
}