3D residual spatial-spectral convolution network for hyperspectral remote sensing image classification

Basit Öğe Kaydı
dc.authoridHanbay, Davut/0000-0003-2271-7865
dc.authoridBAYINDIR, Mehmet ilyas/0000-0003-1999-014X
dc.authoridFIRAT, Huseyin/0000-0002-1257-8518
dc.authorwosidHanbay, Davut/AAG-8511-2019
dc.authorwosidBAYINDIR, Mehmet ilyas/V-6198-2018
dc.authorwosidFIRAT, Huseyin/ABB-7417-2021
dc.contributor.authorFirat, Huseyin
dc.contributor.authorAsker, Mehmet Emin
dc.contributor.authorBayindir, Mehmet Ilyas
dc.contributor.authorHanbay, Davut
dc.date.accessioned2024-08-04T20:53:05Z
dc.date.available2024-08-04T20:53:05Z
dc.date.issued2023
dc.departmentİnönü Üniversitesien_US
dc.description.abstractHyperspectral remote sensing images (HRSI) are 3D image cubes that contain hundreds of spectral bands and have two spatial dimensions and one spectral dimension. HRSI analysis are commonly used in a wide variety of applications such as object detection, precision agriculture and mining. HRSI classification purposes to assign each pixel in HRSI to a unique class. Deep learning is seen as an effective method to improve HRSI classification. In particular, convolutional neural networks (CNNs) are increasingly used in remote sensing field. In this study, a hybrid 3D residual spatial-spectral convolution network (3D-RSSCN) is proposed to extract deep spatiospectral features using 3D CNN and ResNet18 architecture. Simultaneously spatiospectral features extraction is provided using 3D CNN. In deeper CNNs, ResNet architecture is used to achieve higher classification performance as the number of layers increases. In addition, thanks to the ResNet architecture, problems such as degradation and vanishing gradient that may occur in deep networks are overcome. The high dimensionality of the HRSIs increases the computational complexity. Thus, most of studies apply dimension reduction as preprocessing. In the proposed study, principal component analysis (PCA) is used as the preprocessing step for optimum spectral band extraction. The proposed 3D-RSSCN method is tested with Indian pines, Pavia University and Salinas datasets and compared against various deep learning-based methods (SAE, RPNet, 2D CNN, 3D CNN, M3D CNN, HybridSN, FC3D CNN, SSRN, FuSENet, S3EResBoF). As a result of the applications, the best classification accuracy among these methods compared in all datasets is obtained with the proposed 3D-RSSCN. The proposed 3D-RSSCN method has the best accuracy and time performance in classifying.en_US
dc.identifier.doi10.1007/s00521-022-07933-8
dc.identifier.endpage4497en_US
dc.identifier.issn0941-0643
dc.identifier.issn1433-3058
dc.identifier.issue6en_US
dc.identifier.scopus2-s2.0-85140414380en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage4479en_US
dc.identifier.urihttps://doi.org/10.1007/s00521-022-07933-8
dc.identifier.urihttps://hdl.handle.net/11616/100958
dc.identifier.volume35en_US
dc.identifier.wosWOS:000871513400001en_US
dc.identifier.wosqualityQ2en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer London Ltden_US
dc.relation.ispartofNeural Computing & Applicationsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectRemote sensingen_US
dc.subjectHyperspectral image classificationen_US
dc.subjectResNeten_US
dc.subject3D convolutional neural networken_US
dc.subjectPrincipal component analysisen_US
dc.title3D residual spatial-spectral convolution network for hyperspectral remote sensing image classificationen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu