Skip to Main content Skip to Navigation
Conference papers

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

Gilles Simon 1 Antoine Fond 1 Marie-Odile Berger 1 
1 MAGRIT - Visual Augmentation of Complex Environments
Inria Nancy - Grand Est, LORIA - ALGO - Department of Algorithms, Computation, Image and Geometry
Abstract : We show that, in images of man-made environments, the horizon line can usually be hypothesized based on a-contrario detections 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Gilles Simon Connect in order to contact the contributor
Submitted on : Friday, August 31, 2018 - 11:14:54 AM
Last modification on : Saturday, June 25, 2022 - 7:41:09 PM
Long-term archiving on: : Saturday, December 1, 2018 - 1:28:50 PM


Files produced by the author(s)


  • HAL Id : hal-01865251, version 1



Gilles Simon, Antoine Fond, Marie-Odile Berger. A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws. ECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.323-338. ⟨hal-01865251⟩



Record views


Files downloads