CLASSIFICATION OF VHR REMOTE SENSING IMAGES USING LOCAL FEATURE-BASED ATTRIBUTE PROFILES

Minh-Tan Pham 1 Sébastien Lefèvre 1 Erchan Aptoula 2, 1 Bharath Bhushan Damodaran 1
1 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : The present paper introduces an extension of attribute profiles (APs) by extracting their local features. The so-called local feature-based attribute profiles (LFAPs) are expected to provide a better characterization of each APs' filtered pixel (i.e. APs' sample) within its neighborhood, hence better deal with local texture information from the image's content. In this work, LFAP is constructed by extracting some simple first-order statistical features of the local patch around each APs' sample such as mean, standard deviation, range, etc. Then, the final feature vector characterizing each image pixel is formed by combining all local features extracted from APs of that pixel. In order to evaluate the effectiveness of the proposed technique, supervised classification using Random Forest classifier is performed on the VHR panchromatic Reykjavik image. Experimental results show that LFAPs can considerably improve the classification accuracy of the standard APs and the recently proposed histogram-based APs.
Type de document :
Communication dans un congrès
IGARSS 2017, Jul 2017, Fort Worth, United States
Liste complète des métadonnées

Littérature citée [6 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01588290
Contributeur : Minh-Tan Pham <>
Soumis le : lundi 18 septembre 2017 - 16:50:02
Dernière modification le : vendredi 22 septembre 2017 - 01:09:47

Fichier

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

Identifiants

  • HAL Id : hal-01588290, version 1

Citation

Minh-Tan Pham, Sébastien Lefèvre, Erchan Aptoula, Bharath Bhushan Damodaran. CLASSIFICATION OF VHR REMOTE SENSING IMAGES USING LOCAL FEATURE-BASED ATTRIBUTE PROFILES. IGARSS 2017, Jul 2017, Fort Worth, United States. 〈hal-01588290〉

Partager

Métriques

Consultations de
la notice

78

Téléchargements du document

14