ML Anthology

Geodesic Object Proposals

Philipp Krähenbühl, Vladlen Koltun
ECCV 2014 pp. 725-739
doi:10.1007/978-3-319-10602-1_47 /eccv/2014/krahenbuhl2014eccv-geodesic/

Abstract

We present an approach for identifying a set of candidate objects in a given image. This set of candidates can be used for object recognition, segmentation, and other object-based image parsing tasks. To generate the proposals, we identify critical level sets in geodesic distance transforms computed for seeds placed in the image. The seeds are placed by specially trained classifiers that are optimized to discover objects. Experiments demonstrate that the presented approach achieves significantly higher accuracy than alternative approaches, at a fraction of the computational cost.

PDF ECCV Semantic Scholar

Cite

Text

Krähenbühl and Koltun. "Geodesic Object Proposals." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10602-1_47

Markdown

[Krähenbühl and Koltun. "Geodesic Object Proposals." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/krahenbuhl2014eccv-geodesic/) doi:10.1007/978-3-319-10602-1_47

BibTeX

@inproceedings{krahenbuhl2014eccv-geodesic,
  title     = {{Geodesic Object Proposals}},
  author    = {Krähenbühl, Philipp and Koltun, Vladlen},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {725-739},
  doi       = {10.1007/978-3-319-10602-1_47},
  url       = {https://mlanthology.org/eccv/2014/krahenbuhl2014eccv-geodesic/}
}