We propose a strategy for land use classification, which exploits multiple kernel learning (MKL) to automatically determine a suitable combination of a set of features without requiring any heuristic knowledge about the classification task. We present a novel procedure that allows MKL to achieve good performance in the case of small training sets. Experimental results on publicly available data sets demonstrate the feasibility of the proposed approach.

Cusano, C., Napoletano, P., Schettini, R. (2015). Remote Sensing Image Classification Exploiting Multiple Kernel Learning. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 12(11), 2331-2335 [10.1109/LGRS.2015.2476365].

Remote Sensing Image Classification Exploiting Multiple Kernel Learning

CUSANO, CLAUDIO
;
NAPOLETANO, PAOLO
Secondo
;
SCHETTINI, RAIMONDO
Ultimo
2015

Abstract

We propose a strategy for land use classification, which exploits multiple kernel learning (MKL) to automatically determine a suitable combination of a set of features without requiring any heuristic knowledge about the classification task. We present a novel procedure that allows MKL to achieve good performance in the case of small training sets. Experimental results on publicly available data sets demonstrate the feasibility of the proposed approach.
Articolo in rivista - Articolo scientifico
Accuracy; Kernel; Optimization; Remote sensing; Satellites; Standards; Training; Electrical and Electronic Engineering; Geotechnical Engineering and Engineering Geology
English
2331
2335
5
Cusano, C., Napoletano, P., Schettini, R. (2015). Remote Sensing Image Classification Exploiting Multiple Kernel Learning. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 12(11), 2331-2335 [10.1109/LGRS.2015.2476365].
Cusano, C; Napoletano, P; Schettini, R
File in questo prodotto:
File Dimensione Formato  
grsl_2015.pdf

Solo gestori archivio

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 1.16 MB
Formato Adobe PDF
1.16 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
cusano2015remote-sensing.pdf

Solo gestori archivio

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 1.16 MB
Formato Adobe PDF
1.16 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/107308
Citazioni
  • Scopus 17
  • ???jsp.display-item.citation.isi??? 15
Social impact