A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws

Gilles Simon, Antoine Fond, Marie-Odile Berger

ECCV 2018

doi:10.1007/978-3-030-01249-6_20 /eccv/2018/simon2018eccv-acontrario/

Abstract

We show that, in images of man-made environments, the horizon line can usually be hypothesized based on an a contrario detection of second-order grouping events. This allows constraining the extraction of the horizontal vanishing points on that line, thus reducing false detections. Experiments made on three datasets show that our method, not only achieves state-of-the-art performance w.r.t. horizon line detection on two datasets, but also yields much less spurious vanishing points than the previous top-ranked methods.

PDF ECCV Semantic Scholar

Cite

Text

Simon et al. "A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01249-6_20

Markdown

[Simon et al. "A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/simon2018eccv-acontrario/) doi:10.1007/978-3-030-01249-6_20

BibTeX

@inproceedings{simon2018eccv-acontrario,
  title     = {{A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws}},
  author    = {Simon, Gilles and Fond, Antoine and Berger, Marie-Odile},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2018},
  doi       = {10.1007/978-3-030-01249-6_20},
  url       = {https://mlanthology.org/eccv/2018/simon2018eccv-acontrario/}
}