Segmentation and classification of hyperspectral data using watershed

Abstract : The paper presents a new segmentation and classification scheme to analyze hyperspectral (HS) data. The Robust Color Morphological Gradient of the HS image is computed, and the watershed transformation is applied to the obtained gradient. After the pixel-wise Support Vector Machines classification, the majority voting within the watershed regions is performed. Experimental results are presented on a 103-airborne ROSIS image, of the University of Pavia, Italy. The integration of the spatial information from the watershed segmentation into the HS image classification improves the classification accuracies, when compared to the pixel-wise classification.
Type de document :
Communication dans un congrès
IEEE IGARSS'08 - International Geoscience and Remote Sensing Symposium, Jul 2008, Boston, MA, United States. IEEE, Proceedings of the IEEE International Geoscience And Remote Sensing Symposium 2008, IGARSS 2008, 3, pp.652-655, 2008, <10.1109/IGARSS.2008.4779432>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00372311
Contributeur : Jocelyn Chanussot <>
Soumis le : mardi 31 mars 2009 - 20:33:04
Dernière modification le : mardi 12 septembre 2017 - 11:40:46

Identifiants

Citation

Yuliya Tarabalka, Jocelyn Chanussot, Jon Atli Benediktsson, Jesus Angulo, Mathieu Fauvel. Segmentation and classification of hyperspectral data using watershed. IEEE IGARSS'08 - International Geoscience and Remote Sensing Symposium, Jul 2008, Boston, MA, United States. IEEE, Proceedings of the IEEE International Geoscience And Remote Sensing Symposium 2008, IGARSS 2008, 3, pp.652-655, 2008, <10.1109/IGARSS.2008.4779432>. <hal-00372311>

Partager

Métriques

Consultations de la notice

145