Building detection in very high resolution multispectral data with deep learning features

Maria Vakalopoulou 1, 2 Konstantinos Karantzalos 2 Nikos Komodakis 3, 1 Nikos Paragios 4
3 IMAGINE [Marne-la-Vallée]
CSTB - Centre Scientifique et Technique du Bâtiment, LIGM - Laboratoire d'Informatique Gaspard-Monge, ENPC - École des Ponts ParisTech
Abstract : The automated man-made object detection and building extraction from single satellite images is, still, one of the most challenging tasks for various urban planning and monitoring engineering applications. To this end, in this paper we propose an automated building detection framework from very high resolution remote sensing data based on deep convolu-tional neural networks. The core of the developed method is based on a supervised classification procedure employing a very large training dataset. An MRF model is then responsible for obtaining the optimal labels regarding the detection of scene buildings. The experimental results and the performed quantitative validation indicate the quite promising potentials of the developed approach.
Type de document :
Communication dans un congrès
Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International, Jul 2015, Milan, Italy. pp.1873-1876, 2015, 〈10.1109/IGARSS.2015.7326158〉
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01264084
Contributeur : Maria Vakalopoulou <>
Soumis le : mardi 2 février 2016 - 15:25:07
Dernière modification le : mercredi 3 octobre 2018 - 01:10:41
Document(s) archivé(s) le : vendredi 11 novembre 2016 - 18:56:49

Fichier

igarss_vak15.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Maria Vakalopoulou, Konstantinos Karantzalos, Nikos Komodakis, Nikos Paragios. Building detection in very high resolution multispectral data with deep learning features. Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International, Jul 2015, Milan, Italy. pp.1873-1876, 2015, 〈10.1109/IGARSS.2015.7326158〉. 〈hal-01264084〉

Partager

Métriques

Consultations de la notice

688

Téléchargements de fichiers

1553