Image parsing with graph grammars and Markov Random Fields applied to facade analysis

Mateusz Kozinski 1, 2 Renaud Marlet 1, 2
1 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
Abstract : Existing approaches to parsing images of objects featuring complex, non-hierarchical structure rely on exploration of a large search space combining the structure of the object and positions of its parts. The latter task requires randomized or greedy algorithms that do not produce repeatable results or strongly depend on the initial solution. To address the problem we propose to model and optimize the structure of the object and position of its parts separately. We encode the possible object structures in a graph grammar. Then, for a given structure, the positions of the parts are inferred using standard MAP-MRF techniques. This way we limit the application of the less reliable greedy or randomized optimization algorithm to structure inference. We apply our method to parsing images of building facades. The results of our experiments compare favorably to the state of the art.
Type de document :
Communication dans un congrès
2014 IEEE Winter Conference on Applications of Computer Vision (WACV), Mar 2014, Steamboat Springs, CO, United States. pp.729-736, 〈10.1109/WACV.2014.6836030〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01095284
Contributeur : Mateusz Kozinski <>
Soumis le : jeudi 25 juin 2015 - 08:20:43
Dernière modification le : jeudi 5 juillet 2018 - 14:29:05
Document(s) archivé(s) le : vendredi 9 octobre 2015 - 17:23:55

Fichier

WACV-2014-Kozinski-Marlet.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Mateusz Kozinski, Renaud Marlet. Image parsing with graph grammars and Markov Random Fields applied to facade analysis. 2014 IEEE Winter Conference on Applications of Computer Vision (WACV), Mar 2014, Steamboat Springs, CO, United States. pp.729-736, 〈10.1109/WACV.2014.6836030〉. 〈hal-01095284〉

Partager

Métriques

Consultations de la notice

245

Téléchargements de fichiers

77