Feature Matching for Object Localization in the Presence of Uncertainty

Cass, Todd A.

doi:10.1109/ICCV.1990.139551

Feature Matching for Object Localization in the Presence of Uncertainty

Todd A. Cass

ICCV 1990 pp. 360-364

doi:10.1109/ICCV.1990.139551 /iccv/1990/cass1990iccv-feature/

Abstract

The author focuses on the central problem of image and model feature matching. In particular he defines a model of the geometrical uncertainty of image features, and devises a tractable algorithm for determining all feasible sets of feature correspondences given the uncertainty tolerances. A key insight into the matching problem provided by this work is that the search for a matching should be guided by analysis of (feasible) transformation space rather than the space of feature correspondences. This is because the author is only interested in maximal feasible match-sets and not the exponentially many subsets of them as found by correspondence space search.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

ICCV Semantic Scholar

Cite

Text

Cass. "Feature Matching for Object Localization in the Presence of Uncertainty." IEEE/CVF International Conference on Computer Vision, 1990. doi:10.1109/ICCV.1990.139551

Markdown

[Cass. "Feature Matching for Object Localization in the Presence of Uncertainty." IEEE/CVF International Conference on Computer Vision, 1990.](https://mlanthology.org/iccv/1990/cass1990iccv-feature/) doi:10.1109/ICCV.1990.139551

BibTeX

@inproceedings{cass1990iccv-feature,
  title     = {{Feature Matching for Object Localization in the Presence of Uncertainty}},
  author    = {Cass, Todd A.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1990},
  pages     = {360-364},
  doi       = {10.1109/ICCV.1990.139551},
  url       = {https://mlanthology.org/iccv/1990/cass1990iccv-feature/}
}