ML Anthology

ORB: An Efficient Alternative to SIFT or SURF

Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary R. Bradski
ICCV 2011 pp. 2564-2571
doi:10.1109/ICCV.2011.6126544 /iccv/2011/rublee2011iccv-orb/

Abstract

Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for detection and matching. In this paper, we propose a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise. We demonstrate through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations. The efficiency is tested on several real-world applications, including object detection and patch-tracking on a smart phone.

ICCV Semantic Scholar

Cite

Text

Rublee et al. "ORB: An Efficient Alternative to SIFT or SURF." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126544

Markdown

[Rublee et al. "ORB: An Efficient Alternative to SIFT or SURF." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/rublee2011iccv-orb/) doi:10.1109/ICCV.2011.6126544

BibTeX

@inproceedings{rublee2011iccv-orb,
  title     = {{ORB: An Efficient Alternative to SIFT or SURF}},
  author    = {Rublee, Ethan and Rabaud, Vincent and Konolige, Kurt and Bradski, Gary R.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {2564-2571},
  doi       = {10.1109/ICCV.2011.6126544},
  url       = {https://mlanthology.org/iccv/2011/rublee2011iccv-orb/}
}