ML Anthology

Bridging the Gaps Between Cameras

Dimitrios Makris, Tim Ellis, James Black
CVPR 2004 pp. 205-210
doi:10.1109/CVPR.2004.53 /cvpr/2004/makris2004cvpr-bridging/

Abstract

The paper investigates the unsupervised learning of a model of activity for a multi-camera surveillance network that can be created from a large set of observations. This enables the learning algorithm to establish links between camera views associated with an activity. The learning algorithm operates in a correspondence-free manner, exploiting the statistical consistency of the observation data. The derived model is used to automatically determine the topography of a network of cameras and to provide a means for tracking targets across the "blind" areas of the network. A theoretical justification and experimental validation of the methods are provided.

CVPR Semantic Scholar

Cite

Text

Makris et al. "Bridging the Gaps Between Cameras." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.53

Markdown

[Makris et al. "Bridging the Gaps Between Cameras." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/makris2004cvpr-bridging/) doi:10.1109/CVPR.2004.53

BibTeX

@inproceedings{makris2004cvpr-bridging,
  title     = {{Bridging the Gaps Between Cameras}},
  author    = {Makris, Dimitrios and Ellis, Tim and Black, James},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {205-210},
  doi       = {10.1109/CVPR.2004.53},
  url       = {https://mlanthology.org/cvpr/2004/makris2004cvpr-bridging/}
}