ML Anthology

Illumination-Invariant Tracking via Graph Cuts

Daniel Freedman, Matthew W. Turek
CVPR 2005 pp. 10-17
doi:10.1109/CVPR.2005.182 /cvpr/2005/freedman2005cvpr-illumination/

Abstract

Illumination changes are a ubiquitous problem in computer vision. They present a challenge in many applications, including tracking: for example, an object may move in and out of a shadow. We present a new tracking algorithm which is insensitive to illumination changes, while at the same time using all of the available photometric information. The algorithm is based on computing an illumination-invariant optical flow field; the computation is made robust by using a graph cuts formulation. Experimentally, the new technique is shown to quite reliable in both synthetic and real sequences, dealing with a variety of illumination changes that cause problems for density based trackers.

CVPR Semantic Scholar

Cite

Text

Freedman and Turek. "Illumination-Invariant Tracking via Graph Cuts." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.182

Markdown

[Freedman and Turek. "Illumination-Invariant Tracking via Graph Cuts." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/freedman2005cvpr-illumination/) doi:10.1109/CVPR.2005.182

BibTeX

@inproceedings{freedman2005cvpr-illumination,
  title     = {{Illumination-Invariant Tracking via Graph Cuts}},
  author    = {Freedman, Daniel and Turek, Matthew W.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {10-17},
  doi       = {10.1109/CVPR.2005.182},
  url       = {https://mlanthology.org/cvpr/2005/freedman2005cvpr-illumination/}
}