Combining Extended Dependency Tree –HMM based Recognition and Unsupervised Segmentation for Land Cover Mapping in Aerial Images

Mohamed El Yazid Boudaren 1 Abdel Belaïd 2
2 READ - READ
LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : An important challenge to any image pixels classification system is to correctly assign each pixel to its proper class without blurring edges delimiting neighboring regions. In this paper, we present an aerial image mapping approach that advantageously combines unsupervised segmentation with a supervised Markov model based recognition. The originality of the proposed system carries on three concepts: the introduction of an auto-adaptive circular-like window size while applying our stochastic classification to preserve region edges, the extension of the Dependency Tree –HMM to permit the computation of likelihood probability on windows of different shapes and sizes and a mechanism that checks the coherence of the indexing by integrating both segmentations results: from unsupervised over segmentation, regions are assigned to the predominating class with a focus on inner region pixels. To validate our approach, we achieved experiments on real world high resolution aerial images. The obtained results outperform those obtained by supervised classification alone.
Type de document :
Communication dans un congrès
International Conference of Signal and Image Engineering - ICSIE 2009, Jul 2009, London, United Kingdom. Newswood Limited, 2009
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00395327
Contributeur : Mohamed El Yazid Boudaren <>
Soumis le : lundi 15 juin 2009 - 14:18:40
Dernière modification le : lundi 5 novembre 2018 - 16:28:02
Document(s) archivé(s) le : vendredi 11 juin 2010 - 00:47:31

Fichier

BoudarenWCE09b.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00395327, version 1

Collections

Citation

Mohamed El Yazid Boudaren, Abdel Belaïd. Combining Extended Dependency Tree –HMM based Recognition and Unsupervised Segmentation for Land Cover Mapping in Aerial Images. International Conference of Signal and Image Engineering - ICSIE 2009, Jul 2009, London, United Kingdom. Newswood Limited, 2009. 〈inria-00395327〉

Partager

Métriques

Consultations de la notice

172

Téléchargements de fichiers

133