A group-lasso active set strategy for multiclass hyperspectral image classification

Abstract : Hyperspectral images have a strong potential for landcover/landuse classification, since the spectra of the pixels can highlight subtle differences between materials and provide information beyond the visible spectrum. Yet, a limitation of most current approaches is the hypothesis of spatial independence between samples: images are spatially correlated and the classification map should exhibit spatial regularity. One way of integrating spatial smoothness is to augment the input spectral space with filtered versions of the bands. However, open questions remain, such as the selection of the bands to be filtered, or the filterbank to be used. In this paper, we consider the entirety of the possible spatial filters by using an incremental feature learning strategy that assesses whether a candidate feature would improve the model if added to the current input space. Our approach is based on a multiclass logistic classifier with group-lasso regularization. The optimization of this classifier yields an optimality condition, that can easily be used to assess the interest of a candidate feature without retraining the model, thus allowing drastic savings in computational time. We apply the proposed method to three challenging hyperspectral classification scenarios, including agricultural and urban data, and study both the ability of the incremental setting to learn features that always improve the model and the nature of the features selected.
Type de document :
Communication dans un congrès
Photogrammetric Computer Vision (PCV), Sep 2014, Zürich, Switzerland. pp.1--9, 2014
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01063450
Contributeur : Nicolas Courty <>
Soumis le : vendredi 12 septembre 2014 - 10:53:03
Dernière modification le : jeudi 9 février 2017 - 16:04:24
Document(s) archivé(s) le : samedi 13 décembre 2014 - 10:36:56

Fichier

TuiaAS-2014-pcv.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01063450, version 1

Citation

Devis Tuia, Nicolas Courty, Rémi Flamary. A group-lasso active set strategy for multiclass hyperspectral image classification. Photogrammetric Computer Vision (PCV), Sep 2014, Zürich, Switzerland. pp.1--9, 2014. <hal-01063450>

Partager

Métriques

Consultations de
la notice

499

Téléchargements du document

190