ML Anthology

Tracking Objects Across Cameras by Incrementally Learning Inter-Camera Colour Calibration and Patterns of Activity

Andrew Gilbert, Richard Bowden
ECCV 2006 pp. 125-136
doi:10.1007/11744047_10 /eccv/2006/gilbert2006eccv-tracking/

Abstract

This paper presents a scalable solution to the problem of tracking objects across spatially separated, uncalibrated, non-overlapping cameras. Unlike other approaches this technique uses an incremental learning method, to model both the colour variations and posterior probability distributions of spatio-temporal links between cameras. These operate in parallel and are then used with an appearance model of the object to track across spatially separated cameras. The approach requires no pre-calibration or batch preprocessing, is completely unsupervised, and becomes more accurate over time as evidence is accumulated.

PDF ECCV Semantic Scholar

Cite

Text

Gilbert and Bowden. "Tracking Objects Across Cameras by Incrementally Learning Inter-Camera Colour Calibration and Patterns of Activity." European Conference on Computer Vision, 2006. doi:10.1007/11744047_10

Markdown

[Gilbert and Bowden. "Tracking Objects Across Cameras by Incrementally Learning Inter-Camera Colour Calibration and Patterns of Activity." European Conference on Computer Vision, 2006.](https://mlanthology.org/eccv/2006/gilbert2006eccv-tracking/) doi:10.1007/11744047_10

BibTeX

@inproceedings{gilbert2006eccv-tracking,
  title     = {{Tracking Objects Across Cameras by Incrementally Learning Inter-Camera Colour Calibration and Patterns of Activity}},
  author    = {Gilbert, Andrew and Bowden, Richard},
  booktitle = {European Conference on Computer Vision},
  year      = {2006},
  pages     = {125-136},
  doi       = {10.1007/11744047_10},
  url       = {https://mlanthology.org/eccv/2006/gilbert2006eccv-tracking/}
}