ML Anthology

Tracking Multiple People Under Global Appearance Constraints

Horesh Ben Shitrit, Jérôme Berclaz, François Fleuret, Pascal Fua
ICCV 2011 pp. 137-144
doi:10.1109/ICCV.2011.6126235 /iccv/2011/shitrit2011iccv-tracking/

Abstract

In this paper, we show that tracking multiple people whose paths may intersect can be formulated as a convex global optimization problem. Our proposed framework is designed to exploit image appearance cues to prevent identity switches. Our method is effective even when such cues are only available at distant time intervals. This is unlike many current approaches that depend on appearance being exploitable from frame to frame. We validate our approach on three multi-camera sport and pedestrian datasets that contain long and complex sequences. Our algorithm perseveres identities better than state-of-the-art algorithms while keeping similar MOTA scores.

PDF ICCV Semantic Scholar

Cite

Text

Shitrit et al. "Tracking Multiple People Under Global Appearance Constraints." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126235

Markdown

[Shitrit et al. "Tracking Multiple People Under Global Appearance Constraints." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/shitrit2011iccv-tracking/) doi:10.1109/ICCV.2011.6126235

BibTeX

@inproceedings{shitrit2011iccv-tracking,
  title     = {{Tracking Multiple People Under Global Appearance Constraints}},
  author    = {Shitrit, Horesh Ben and Berclaz, Jérôme and Fleuret, François and Fua, Pascal},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {137-144},
  doi       = {10.1109/ICCV.2011.6126235},
  url       = {https://mlanthology.org/iccv/2011/shitrit2011iccv-tracking/}
}