Active learning methods for remote sensing image classification

Détails

ID Serval
serval:BIB_83C1967A0877
Type
Article: article d'un périodique ou d'un magazine.
Collection
Publications
Institution
Titre
Active learning methods for remote sensing image classification
Périodique
IEEE Transactions on Geoscience and Remote Sensing
Auteur(s)
Tuia D., Ratle F., Pacifici F., Kanevski M., Emery W.J.
ISSN
0196-2892
Statut éditorial
Publié
Date de publication
07/2009
Peer-reviewed
Oui
Volume
47
Numéro
7
Pages
2218-2232
Langue
anglais
Résumé
In this paper, we propose two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification. Based on predefined heuristics, the classifier ranks the unlabeled pixels and automatically chooses those that are considered the most valuable for its improvement. Once the pixels have been selected, the analyst labels them manually and the process is iterated. Starting with a small and nonoptimal training set, the model itself builds the optimal set of samples which minimizes the classification error. We have applied the proposed algorithms to a variety of remote sensing data, including very high resolution and hyperspectral images, using support vector machines. Experimental results confirm the consistency of the methods. The required number of training samples can be reduced to 10% using the methods proposed, reaching the same level of accuracy as larger data sets. A comparison with a state-of-the-art active learning method, margin sampling, is provided, highlighting advantages of the methods proposed. The effect of spatial resolution and separability of the classes on the quality of the selection of pixels is also discussed.
Mots-clé
Active learning, entropy, hyperspectral imagery, image information mining, margin sampling (MS), query learning, support vector machines (SVMs), very high resolution (VHR) imagery
Web of science
Création de la notice
04/02/2009 18:32
Dernière modification de la notice
20/08/2019 15:43
Données d'usage