ML Anthology

Real-Time Feature Tracking and Outlier Rejection with Changes in Illumination

Hailin Jin, Paolo Favaro, Stefano Soatto
ICCV 2001 pp. 684-689
doi:10.1109/ICCV.2001.10073 /iccv/2001/jin2001iccv-real/

Abstract

We develop an efficient algorithm to track point features supported by image patches undergoing affine deformations and changes in illumination. The algorithm is based on a combined model of geometry and photometry, that is used to track features as well as to detect outliers in a hypothesis testing framework. The algorithm runs in real time on a personal computer; and is available to the public.

ICCV Semantic Scholar

Cite

Text

Jin et al. "Real-Time Feature Tracking and Outlier Rejection with Changes in Illumination." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.10073

Markdown

[Jin et al. "Real-Time Feature Tracking and Outlier Rejection with Changes in Illumination." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/jin2001iccv-real/) doi:10.1109/ICCV.2001.10073

BibTeX

@inproceedings{jin2001iccv-real,
  title     = {{Real-Time Feature Tracking and Outlier Rejection with Changes in Illumination}},
  author    = {Jin, Hailin and Favaro, Paolo and Soatto, Stefano},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {684-689},
  doi       = {10.1109/ICCV.2001.10073},
  url       = {https://mlanthology.org/iccv/2001/jin2001iccv-real/}
}