Header

UZH-Logo

Maintenance Infos

Multiclass feature learning for hyperspectral image classification: Sparse and hierarchical solutions


Tuia, Devis; Flamary, Rémi; Courty, Nicolas (2015). Multiclass feature learning for hyperspectral image classification: Sparse and hierarchical solutions. ISPRS Journal of Photogrammetry and Remote Sensing, 105:272-285.

Abstract

In this paper, we tackle the question of discovering an effective set of spatial filters to solve hyperspectral classification problems. Instead of fixing a priori the filters and their parameters using expert knowledge, we let the model find them within random draws in the (possibly infinite) space of possible filters. We define an active set feature learner that includes in the model only features that improve the classifier. To this end, we consider a fast and linear classifier, multiclass logistic classification, and show that with a good representation (the filters discovered), such a simple classifier can reach at least state of the art performances. We apply the proposed active set learner in four hyperspectral image classification problems, including agricultural and urban classification at different resolutions, as well as multimodal data. We also propose a hierarchical setting, which allows to generate more complex banks of features that can better describe the nonlinearities present in the data.

Abstract

In this paper, we tackle the question of discovering an effective set of spatial filters to solve hyperspectral classification problems. Instead of fixing a priori the filters and their parameters using expert knowledge, we let the model find them within random draws in the (possibly infinite) space of possible filters. We define an active set feature learner that includes in the model only features that improve the classifier. To this end, we consider a fast and linear classifier, multiclass logistic classification, and show that with a good representation (the filters discovered), such a simple classifier can reach at least state of the art performances. We apply the proposed active set learner in four hyperspectral image classification problems, including agricultural and urban classification at different resolutions, as well as multimodal data. We also propose a hierarchical setting, which allows to generate more complex banks of features that can better describe the nonlinearities present in the data.

Statistics

Citations

22 citations in Web of Science®
28 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

1 download since deposited on 09 Oct 2015
0 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
Dewey Decimal Classification:910 Geography & travel
Language:English
Date:2015
Deposited On:09 Oct 2015 15:26
Last Modified:05 Apr 2016 19:26
Publisher:Elsevier
ISSN:0924-2716
Publisher DOI:https://doi.org/10.1016/j.isprsjprs.2015.01.006

Download