000867900 001__ 867900
000867900 005__ 20230918092306.0
000867900 0247_ $$2doi$$a10.1109/IGARSS.2019.8899831
000867900 0247_ $$2Handle$$a2128/23600
000867900 0247_ $$2WOS$$aWOS:000519270601013
000867900 037__ $$aFZJ-2019-06502
000867900 1001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b0$$eCorresponding author$$ufzj
000867900 1112_ $$aIGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium$$cYokohama$$d2019-07-28 - 2019-08-02$$wJapan
000867900 245__ $$aMulti-Scale Convolutional SVM Networks for Multi-Class Classification Problems of Remote Sensing Images
000867900 260__ $$bIEEE$$c2019
000867900 29510 $$a[Proceedings] - IEEE, 2019. - ISBN 978-1-5386-9154-0 
000867900 300__ $$a875-878
000867900 3367_ $$2ORCID$$aCONFERENCE_PAPER
000867900 3367_ $$033$$2EndNote$$aConference Paper
000867900 3367_ $$2BibTeX$$aINPROCEEDINGS
000867900 3367_ $$2DRIVER$$aconferenceObject
000867900 3367_ $$2DataCite$$aOutput Types/Conference Paper
000867900 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1576507707_30946
000867900 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000867900 520__ $$aThe classification of land-cover classes in remote sensing images can suit a variety of interdisciplinary applications suchas the interpretation of natural and man-made processes onthe Earth surface. The Convolutional Support Vector Machine (CSVM) network was recently proposed as binary classifier for the detection of objects in Unmanned Aerial Vehicle (UAV) images. The training phase of the CSVM isbased on convolutional layers that learn the kernel weightsvia a set of linear Support Vector Machines (SVMs). Thispaper proposes the Multi-scale Convolutional Support VectorMachine (MCSVM) network, that is an ensemble of CSVMclassifiers which process patches of different spatial sizes andcan deal with multi-class classification problems. The experiments are carried out on the EuroSAT Sentinel-2 dataset andthe results are compared to the one obtained with recent transfer learning approaches based on pre-trained ConvolutionalNeural Networks (CNNs).
000867900 536__ $$0G:(DE-HGF)POF3-512$$a512 - Data-Intensive Science and Federated Computing (POF3-512)$$cPOF3-512$$fPOF III$$x0
000867900 536__ $$0G:(EU-Grant)754304$$aDEEP-EST - DEEP - Extreme Scale Technologies (754304)$$c754304$$fH2020-FETHPC-2016$$x1
000867900 536__ $$0G:(EU-Grant)604102$$aHBP - The Human Brain Project (604102)$$c604102$$fFP7-ICT-2013-FET-F$$x2
000867900 588__ $$aDataset connected to CrossRef Conference
000867900 7001_ $$0P:(DE-HGF)0$$aBazi, Yakoub$$b1
000867900 7001_ $$0P:(DE-HGF)0$$aMelgani, Farid$$b2
000867900 7001_ $$0P:(DE-Juel1)132239$$aRiedel, Morris$$b3
000867900 773__ $$a10.1109/IGARSS.2019.8899831
000867900 8564_ $$uhttps://juser.fz-juelich.de/record/867900/files/MCSVM_Cavallaro.pdf$$yOpenAccess
000867900 8564_ $$uhttps://juser.fz-juelich.de/record/867900/files/MCSVM_Cavallaro.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000867900 909CO $$ooai:juser.fz-juelich.de:867900$$pdnbdelivery$$pec_fundedresources$$pVDB$$pdriver$$popen_access$$popenaire
000867900 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b0$$kFZJ
000867900 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132239$$aForschungszentrum Jülich$$b3$$kFZJ
000867900 9131_ $$0G:(DE-HGF)POF3-512$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vData-Intensive Science and Federated Computing$$x0
000867900 9141_ $$y2019
000867900 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000867900 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000867900 980__ $$acontrib
000867900 980__ $$aVDB
000867900 980__ $$aUNRESTRICTED
000867900 980__ $$acontb
000867900 980__ $$aI:(DE-Juel1)JSC-20090406
000867900 9801_ $$aFullTexts