A Stochastic Minimum Spanning Forest approach for spectral-spatial classification of hyperspectral images

Abstract : A new method for supervised hyperspectral data classification is proposed. In particular, the notion of Stochastic Minimum Spanning Forests (MSFs) is introduced. For a given hyper-spectral image, a pixelwise classification is first performed. From this classification map, M marker maps are generated by randomly selecting pixels and labeling them as markers for the construction of MSFs. The next step consists in building an MSF from each of the M marker maps. Finally, all the M realizations are aggregated with a maximum vote decision rule, resulting in a final classification map. The experimental results presented on an AVIRIS image of the vegetation area show that the proposed approach yields accurate classification maps, and thus is attractive for hyperspectral data analysis.
Type de document :
Communication dans un congrès
18th IEEE International Conference on Image Processing (ICIP 2011), Sep 2011, Bruxelles, Belgium. IEEE, 18th IEEE International Conference on Image Processing (ICIP), pp.1265-1268, 2011, 〈10.1109/ICIP.2011.6115664〉
Liste complète des métadonnées

https://hal-mines-paristech.archives-ouvertes.fr/hal-00833516
Contributeur : Bibliothèque Mines Paristech <>
Soumis le : mercredi 12 juin 2013 - 23:06:57
Dernière modification le : vendredi 27 octobre 2017 - 17:36:02

Identifiants

Citation

Kevin Bernard, Yuliya Tarabalka, Jesus Angulo, Jocelyn Chanussot, Jon Atli Benediktsson. A Stochastic Minimum Spanning Forest approach for spectral-spatial classification of hyperspectral images. 18th IEEE International Conference on Image Processing (ICIP 2011), Sep 2011, Bruxelles, Belgium. IEEE, 18th IEEE International Conference on Image Processing (ICIP), pp.1265-1268, 2011, 〈10.1109/ICIP.2011.6115664〉. 〈hal-00833516〉

Partager

Métriques

Consultations de la notice

307