ML Anthology

DARTs: Efficient Scale-Space Extraction of DAISY Keypoints

David Marimon, Arturo Bonnin, Tomasz Adamek, Roger Gimeno
CVPR 2010 pp. 2416-2423
doi:10.1109/CVPR.2010.5539936 /cvpr/2010/marimon2010cvpr-darts/

Abstract

Winder et al. have recently shown the superiority of the DAISY descriptor in comparison to other widely extended descriptors such as SIFT and SURF. Motivated by those results, we present a novel algorithm that extracts viewpoint and illumination invariant keypoints and describes them with a particular implementation of a DAISY-like layout. We demonstrate how to efficiently compute the scale-space and re-use this information for the descriptor. Comparison to similar approaches such as SIFT and SURF show higher precision vs recall performance of the proposed method. Moreover, we dramatically reduce the computational cost by a factor of 6x and 3x, respectively. We also prove the use of the proposed method for computer vision applications.

CVPR Semantic Scholar

Cite

Text

Marimon et al. "DARTs: Efficient Scale-Space Extraction of DAISY Keypoints." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539936

Markdown

[Marimon et al. "DARTs: Efficient Scale-Space Extraction of DAISY Keypoints." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/marimon2010cvpr-darts/) doi:10.1109/CVPR.2010.5539936

BibTeX

@inproceedings{marimon2010cvpr-darts,
  title     = {{DARTs: Efficient Scale-Space Extraction of DAISY Keypoints}},
  author    = {Marimon, David and Bonnin, Arturo and Adamek, Tomasz and Gimeno, Roger},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {2416-2423},
  doi       = {10.1109/CVPR.2010.5539936},
  url       = {https://mlanthology.org/cvpr/2010/marimon2010cvpr-darts/}
}