HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Génération d'hypothèses de façades utilisant des critères contextuels et structurels

Antoine Fond 1, 2, 3, * Marie-Odile Berger 2, 3 Gilles Simon 1, 2, 3
* Corresponding author
3 MAGRIT - Visual Augmentation of Complex Environments
LORIA - ALGO - Department of Algorithms, Computation, Image and Geometry, Inria Nancy - Grand Est
Abstract : In that article we focus on facade detection in order to improve image/model buildings matching for pose computation in urbain environnement. We use a two-step design. First a cascade of LogitBoost classifiers using features which describe local context selects a few windows from a set of windows drawn on an a priori distribution. These facade candidates are then more internally described using their Haar-Fourier representation. Eventually they are discarded or kept by a strong classifier SVM. Results are computed from a 410-set of urban images.
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download

Contributor : Antoine Fond Connect in order to contact the contributor
Submitted on : Thursday, May 19, 2016 - 6:00:17 PM
Last modification on : Wednesday, November 3, 2021 - 7:08:53 AM


Files produced by the author(s)


  • HAL Id : hal-01318680, version 1



Antoine Fond, Marie-Odile Berger, Gilles Simon. Génération d'hypothèses de façades utilisant des critères contextuels et structurels. Reconnaissance des Formes et Intelligence Artificielle, Jun 2016, Clermont Ferrand, France. ⟨hal-01318680⟩



Record views


Files downloads