ML Anthology

Compact Signatures for High-Speed Interest Point Description and Matching

Michael Calonder, Vincent Lepetit, Pascal Fua, Kurt Konolige, James Bowman, Patrick Mihelich
ICCV 2009 pp. 357-364
doi:10.1109/ICCV.2009.5459272 /iccv/2009/calonder2009iccv-compact/

Abstract

Prominent feature point descriptors such as SIFT and SURF allow reliable real-time matching but at a computational cost that limits the number of points that can be handled on PCs, and even more on less powerful mobile devices. A recently proposed technique that relies on statistical classification to compute signatures has the potential to be much faster but at the cost of using very large amounts of memory, which makes it impractical for implementation on low-memory devices.

PDF ICCV Semantic Scholar

Cite

Text

Calonder et al. "Compact Signatures for High-Speed Interest Point Description and Matching." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459272

Markdown

[Calonder et al. "Compact Signatures for High-Speed Interest Point Description and Matching." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/calonder2009iccv-compact/) doi:10.1109/ICCV.2009.5459272

BibTeX

@inproceedings{calonder2009iccv-compact,
  title     = {{Compact Signatures for High-Speed Interest Point Description and Matching}},
  author    = {Calonder, Michael and Lepetit, Vincent and Fua, Pascal and Konolige, Kurt and Bowman, James and Mihelich, Patrick},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2009},
  pages     = {357-364},
  doi       = {10.1109/ICCV.2009.5459272},
  url       = {https://mlanthology.org/iccv/2009/calonder2009iccv-compact/}
}