ML Anthology

Feature Selection for Reliable Tracking Using Template Matching

Toshimitsu Kaneko, Osamu Hori
CVPR 2003 pp. 796-802
doi:10.1109/CVPR.2003.1211434 /cvpr/2003/kaneko2003cvpr-feature/

Abstract

A new feature selection method for reliable tracking is presented. In this paper, it is assumed that features are tracked by template matching where small regions around the features are defined as templates. The proposed method selects features based on the upper bound of the average template matching error. This selection criterion is directly related to the reliability of tracking and hence, the performance is better than that of other feature detectors. Experimental results are presented to confirm the efficiency of the proposed method.

CVPR Semantic Scholar

Cite

Text

Kaneko and Hori. "Feature Selection for Reliable Tracking Using Template Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211434

Markdown

[Kaneko and Hori. "Feature Selection for Reliable Tracking Using Template Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/kaneko2003cvpr-feature/) doi:10.1109/CVPR.2003.1211434

BibTeX

@inproceedings{kaneko2003cvpr-feature,
  title     = {{Feature Selection for Reliable Tracking Using Template Matching}},
  author    = {Kaneko, Toshimitsu and Hori, Osamu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {796-802},
  doi       = {10.1109/CVPR.2003.1211434},
  url       = {https://mlanthology.org/cvpr/2003/kaneko2003cvpr-feature/}
}