Create the relevant spatial filterbank in the hyperspectral jungle

Devis Tuia, Michele Volpi, Mauro Dalla Mura, Alain Rakotomamonjy, Remi Flamary

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

Abstract

Inclusion of spatial information is known to be beneficial to the classification of hyperspectral images. However, given the high dimensionality of the data, it is difficult to know before hand which are the bands to filter or what are the filters to be applied. In this paper, we propose an active set algorithm based on a l1 support vector machine that explores the (possibily infinite) space of spatial filters and retrieves automatically the filters that maximize class separation. Experiments on hyperspectral imagery confirms the power of the method, that reaches state of the art performance with small feature sets generated automatically and without prior knowledge.

Original languageEnglish
Title of host publication2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings
Pages2172-2175
Number of pages4
DOIs
Publication statusPublished - 1 Dec 2013
Externally publishedYes
Event2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Melbourne, VIC, Australia
Duration: 21 Jul 201326 Jul 2013

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013
CountryAustralia
CityMelbourne, VIC
Period21/07/1326/07/13

Fingerprint Dive into the research topics of 'Create the relevant spatial filterbank in the hyperspectral jungle'. Together they form a unique fingerprint.

Cite this