Show simple item record

AuthorAhishali M.
AuthorInce T.
AuthorKiranyaz, Mustafa Serkan
AuthorGabbouj M.
Available date2022-04-26T12:31:21Z
Publication Date2019
Publication NameProgress in Electromagnetics Research Symposium
ResourceScopus
Identifierhttp://dx.doi.org/10.1109/PIERS-Spring46901.2019.9017716
URIhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85082018376&doi=10.1109%2fPIERS-Spring46901.2019.9017716&partnerID=40&md5=5fc0508601d861dd8da665a7440e21ad
URIhttp://hdl.handle.net/10576/30620
AbstractIn this work, we propose to use learned features for terrain classification of Polarimetric Synthetic Aperture Radar (PolSAR) images. In the proposed classification framework, the learned features are extracted from sliding window regions using Convolutional Neural Networks (CNNs), and then they are used for the classification with the linear Support Vector Machine (SVM) classifier. The classification performance of the proposed approach is compared with numerous target decomposition theorems (TDs) as the engineered features tested with two classifiers: Collective Network of Binary Classifiers (CNBCs) and SVMs. The experimental evaluations over two commonly used benchmark AIRSAR PolSAR images, San Francisco Bay and Flevoland at L- Band, reveal that the classification performance of the learned features with CNNs outperforms the performance of the engineered features as TDs even the dimension of learned features is the quarter of the engineered features.
Languageen
PublisherInstitute of Electrical and Electronics Engineers Inc.
SubjectBenchmarking
Convolutional neural networks
Domain decomposition methods
Photonics
Piers
Polarimeters
Radar imaging
Support vector machines
Synthetic aperture radar
Classification framework
Classification performance
Experimental evaluation
Linear Support Vector Machines
Performance comparison
Polarimetric synthetic aperture radars
Target decomposition theorems
Terrain classification
Classification (of information)
TitlePerformance Comparison of Learned vs. Engineered Features for Polarimetric SAR Terrain Classification
TypeConference Paper
Pagination2317-2324
Volume Number2019-June
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record