Combining transductive and active learning to improve object-based classification of remote sensing images

Fábio Nór Güttler 1 Dino Ienco 2, 3 Pascal Poncelet 2, 3 Maguelonne Teisseire 3, 2
1 LETG - Brest - Littoral, Environnement, Télédétection, Géomatique
LETG - Littoral, Environnement, Télédétection, Géomatique
2 ADVANSE - ADVanced Analytics for data SciencE
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
3 UMR TETIS - Territoires, Environnement, Télédétection et Information Spatiale
Abstract : In this letter, we propose a new active transductive learning (ATL) framework for object-based classification of satellite images. The framework couples graph-based label propagation with active learning (AL) to exploit positive aspects of the two learning settings. The transductive approach considers both labelled and unlabelled image objects to perform its classification as they are all available at training time while the AL strategy smartly guides the construction of the training set employed by the learner. The proposed framework was tested in the context of a land cover classification task using RapidEye optical imagery. A reference land cover map was elaborated over the whole study area in order to get reliable information about the performance of the ATL framework. The experimental evaluation under- lines that, with a reasonable amount of training data, our framework outperforms state of the art classification methods usually employed in the field of remote sensing.
Type de document :
Article dans une revue
Remote Sensing Letters, Taylor and Francis, 2016, 7 (4), pp.358-367. 〈10.1080/2150704X.2016.1142678〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger
https://hal-lirmm.ccsd.cnrs.fr/lirmm-01275515
Contributeur : Dino Ienco <>
Soumis le : mercredi 17 février 2016 - 15:43:49
Dernière modification le : mardi 5 juin 2018 - 10:14:23
Document(s) archivé(s) le : mercredi 18 mai 2016 - 13:12:13

Fichier

RSL_TransductiveActiveLearning...
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

LIRMM | UR2-HB | UNIV-BREST | IRSTEA | UNIV-NANTES | CIRAD | LETG-GEOMER | LETG | ADVANSE | AGROPOLIS | AGROPARISTECH | UNIV-RENNES2 | MIPS | COMUE-NORMANDIE | UNIV-MONTPELLIER | CMM | IUEM | PSL | UNIV-RENNES

Citation

Fábio Nór Güttler, Dino Ienco, Pascal Poncelet, Maguelonne Teisseire. Combining transductive and active learning to improve object-based classification of remote sensing images. Remote Sensing Letters, Taylor and Francis, 2016, 7 (4), pp.358-367. 〈10.1080/2150704X.2016.1142678〉. 〈lirmm-01275515〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

379

Téléchargements de fichiers

305

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD