Multi-resolution Classification of Urban Areas Using Hierarchical Symmetric Markov Mesh Models

Ihsen Hedhli 1 Gabriele Moser 2 Sebastiano Serpico 2 Josiane Zerubia 3
1 ESPRIT - École Supérieure Privée d'Ingénierie et de Technologie
2 DITEN - Dipartimento di Ingegneria Navale, Elettrica, Elettronica e delle Telecomunicazioni / Dept. of Electrical, Electronic, Telecommunications Engineering and Naval Architecture
3 AYIN - Models of spatio-temporal structure for high-resolution image processing
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : In this paper we investigate a new hierarchical method for high resolution remotely sensed image classification. The proposed approach integrates an explicit hierarchical graph-based classifier, which uses a quad-tree structure to model multi-scale interactions, and a symmetric Markov mesh random field to deal with pixelwise contextual information at the same scale. The choice of a quad-tree and the symmetric Markov mesh allow taking benefit from their good analytical properties (especially causality) and consequently applying time-efficient non-iterative inference algorithms.
Type de document :
Communication dans un congrès
IEEE GRS/ISPRS Joint Urban Remote Sensing Event (JURSE), Mar 2017, Dubai, United Arab Emirates. 2017
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-01415568
Contributeur : Ihsen Hedhli <>
Soumis le : mardi 13 décembre 2016 - 11:57:05
Dernière modification le : samedi 27 janvier 2018 - 01:31:39
Document(s) archivé(s) le : mardi 14 mars 2017 - 12:49:47

Fichier

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

Identifiants

  • HAL Id : hal-01415568, version 1

Collections

INRIA | INRIA2017

Citation

Ihsen Hedhli, Gabriele Moser, Sebastiano Serpico, Josiane Zerubia. Multi-resolution Classification of Urban Areas Using Hierarchical Symmetric Markov Mesh Models. IEEE GRS/ISPRS Joint Urban Remote Sensing Event (JURSE), Mar 2017, Dubai, United Arab Emirates. 2017. 〈hal-01415568〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

280

Téléchargements de fichiers

107

Contact


archive-ouverte@inria.fr