Centre dedocumentation
scientifique

ATLAS: A three-layered approach to facade parsing / Markus Mathias in International journal of computer vision, vol 118 n° 1 (May 2016)  

Public [article]  inInternational journal of computer vision > vol 118 n° 1 (May 2016) . - pp 22 – 48 Titre : ATLAS: A three-layered approach to facade parsing Type de document : Article/Communication Auteurs : Markus Mathias, Auteur ; Anđelo Martinović, Auteur ; Luc Van Gool, Auteur Année de publication : 2016 Article en page(s) : pp 22 – 48 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes descripteurs IGN] analyse d'image numérique [Termes descripteurs IGN] analyse syntaxique [Termes descripteurs IGN] appariement sémantique [Termes descripteurs IGN] classificateur paramétrique [Termes descripteurs IGN] couche [Termes descripteurs IGN] façade [Termes descripteurs IGN] intégration de données [Termes descripteurs IGN] méta connaissance [Termes descripteurs IGN] reconstruction 2D du bâti [Termes descripteurs IGN] style architectural [Termes descripteurs IGN] test de performance Résumé : (auteur) We propose a novel approach for semantic segmentation of building facades. Our system consists of three distinct layers, representing different levels of abstraction in facade images: segments, objects and architectural elements. In the first layer, the facade is segmented into regions, each of which is assigned a probability distribution over semantic classes. We evaluate different state-of-the-art segmentation and classification strategies to obtain the initial probabilistic semantic labeling. In the second layer, we investigate the performance of different object detectors and show the benefit of using such detectors to improve our initial labeling. The generic approaches of the first two layers are then specialized for the task of facade labeling in the third layer. There, we incorporate additional meta-knowledge in the form of weak architectural principles, which enforces architectural plausibility and consistency on the final reconstruction. Rigorous tests performed on two existing datasets of building facades demonstrate that we outperform the current state of the art, even when using outputs from lower layers of the pipeline. Finally, we demonstrate how the output of the highest layer can be used to create a procedural building reconstruction. Numéro de notice : A2016--150 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article En ligne : https://doi.org/10.1007/s11263-015-0868-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85918 [article]

Learning grammars for architecture-specific facade parsing / Raghudeep Gadde in International journal of computer vision, vol 117 n° 3 (May 2016)  

Public [article]  inInternational journal of computer vision > vol 117 n° 3 (May 2016) . - pp 290 – 316 Titre : Learning grammars for architecture-specific facade parsing Type de document : Article/Communication Auteurs : Raghudeep Gadde, Auteur ; Renaud Marlet, Auteur ; Nikos Paragios, Auteur Année de publication : 2016 Article en page(s) : pp 290 – 316 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes descripteurs IGN] algorithme d'apprentissage [Termes descripteurs IGN] analyse de données [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] architecture [Termes descripteurs IGN] façade [Termes descripteurs IGN] réalité de terrain [Termes descripteurs IGN] style architectural Résumé : (auteur) Parsing facade images requires optimal handcrafted grammar for a given class of buildings. Such a handcrafted grammar is often designed manually by experts. In this paper, we present a novel framework to learn a compact grammar from a set of ground-truth images. To this end, parse trees of ground-truth annotated images are obtained running existing inference algorithms with a simple, very general grammar. From these parse trees, repeated subtrees are sought and merged together to share derivations and produce a grammar with fewer rules. Furthermore, unsupervised clustering is performed on these rules, so that, rules corresponding to the same complex pattern are grouped together leading to a rich compact grammar. Experimental validation and comparison with the state-of-the-art grammar-based methods on four different datasets show that the learned grammar helps in much faster convergence while producing equal or more accurate parsing results compared to handcrafted grammars as well as grammars learned by other methods. Besides, we release a new dataset of facade images following the Art-deco style and demonstrate the general applicability and extreme potential of the proposed framework. Numéro de notice : A2016--149 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article En ligne : https://doi.org/10.1007/s11263-016-0887-4 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85917 [article]