Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Assessment of Machine Learning Techniques for Oil Rig Classification in C-Band SAR Images
Aeronautics Institute of Technology (ITA), BRA.
Aeronautics Institute of Technology (ITA), BRA.
Blekinge Tekniska Högskola, Fakulteten för teknikvetenskaper, Institutionen för matematik och naturvetenskap.ORCID-id: 0000-0003-0423-9927
Aeronautics Institute of Technology (ITA), BRA.
2022 (Engelska)Ingår i: Remote Sensing, E-ISSN 2072-4292, Vol. 14, nr 13, artikel-id 2966Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

This article aims at performing maritime target classification in SAR images using machine learning (ML) and deep learning (DL) techniques. In particular, the targets of interest are oil platforms and ships located in the Campos Basin, Brazil. Two convolutional neural networks (CNNs), VGG-16 and VGG-19, were used for attribute extraction. The logistic regression (LR), random forest (RF), support vector machine (SVM), k-nearest neighbours (kNN), decision tree (DT), naive Bayes (NB), neural networks (NET), and AdaBoost (ADBST) schemes were considered for classification. The target classification methods were evaluated using polarimetric images obtained from the C-band synthetic aperture radar (SAR) system Sentinel-1. Classifiers are assessed by the accuracy indicator. The LR, SVM, NET, and stacking results indicate better performance, with accuracy ranging from 84.1% to 85.5%. The Kruskal–Wallis test shows a significant difference with the tested classifier, indicating that some classifiers present different accuracy results. The optimizations provide results with more significant accuracy gains, making them competitive with those shown in the literature. There is no exact combination of methods for SAR image classification that will always guarantee the best accuracy. The optimizations performed in this article were for the specific data set of the Campos Basin, and results may change depending on the data set format and the number of images. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Ort, förlag, år, upplaga, sidor
MDPI , 2022. Vol. 14, nr 13, artikel-id 2966
Nyckelord [en]
classification algorithms, deep learning, machine learning, oil rig classification, SAR, ship classification, Adaptive boosting, Classification (of information), Convolutional neural networks, Decision trees, Image classification, Learning systems, Nearest neighbor search, Radar imaging, Ships, Support vector machines, C-bands, Campos Basin, Classification algorithm, Machine-learning, Oil-rigs, Synthetic aperture radar images, Target Classification, Synthetic aperture radar
Nationell ämneskategori
Fjärranalysteknik
Identifikatorer
URN: urn:nbn:se:bth-23505DOI: 10.3390/rs14132966ISI: 000825692700001Scopus ID: 2-s2.0-85132981546OAI: oai:DiVA.org:bth-23505DiVA, id: diva2:1686807
Anmärkning

open access

Tillgänglig från: 2022-08-11 Skapad: 2022-08-11 Senast uppdaterad: 2023-08-28Bibliografiskt granskad

Open Access i DiVA

fulltext(9761 kB)202 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 9761 kBChecksumma SHA-512
f81d79d0cc142c2160c8de42f32755fca7ba556723775e8bbdc24f94190ed291dde35e051101b1b93df7b831522bfc46447eb62ff6de2d74bdbac8e981dc4150
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextScopus

Person

Palm, Bruna

Sök vidare i DiVA

Av författaren/redaktören
Palm, Bruna
Av organisationen
Institutionen för matematik och naturvetenskap
I samma tidskrift
Remote Sensing
Fjärranalysteknik

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 202 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 172 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf