Multiple-feature Kernel-based Probabilistic Clustering for Unsupervised Band Selection - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Geoscience and Remote Sensing Année : 2019

Multiple-feature Kernel-based Probabilistic Clustering for Unsupervised Band Selection

Résumé

This paper presents a new method to perform unsupervised band selection (UBS) with hyperspectral data. The method provides a probabilistic clustering approach. The band images are clustered in the image space by computing their posterior class probability. Then, for each cluster, the band exhibiting the highest probability of belonging to it is selected as cluster exemplar. More particularly, the proposed method falls into information-maximization clustering methods, where the posterior class probability is modeled and the parameters of the models are derived by maximizing the information between the data and the unknown cluster labels. In this context, we propose a new image representation for hyperspectral images, based on the first and second order statistics of multiple image features. We refer to this representation as multiple-feature local statistical descriptors (MLSD). The descriptors are computed w.r.t. regular grids, and a special pixel selection procedure reduces the number of samples within each block of the grid. A kernel-based model that embeds the MLSD is then proposed for the posterior class probability. The model is finally optimized according to an information-maximization criterion. We conduct several experiments to determine the best parameters for the proposed approach and compare the latter with other state-of-the-art UBS methods. Quantitative evaluations show that, by employing our band selection method, higher performance in terms of classification accuracy and endmember extraction can be achieved in comparison with the state of the art.
Fichier principal
Vignette du fichier
TGRS_2018_UBS_1column.pdf (4.83 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02530242 , version 1 (02-04-2020)

Identifiants

Citer

Marco Bevilacqua, Yannick Berthoumieu. Multiple-feature Kernel-based Probabilistic Clustering for Unsupervised Band Selection. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57 (9), pp.6675-6689. ⟨10.1109/TGRS.2019.2907924⟩. ⟨hal-02530242⟩
27 Consultations
105 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More