Assessment of Machine Learning Techniques for Oil Rig Classification in C-Band SAR Images

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2022-07, Vol.14 (13), p.2966
• Main Authors: da Silva, Fabiano G., Ramos, Lucas P., Palm, Bruna G., Machado, Renato
• Format: Article
• Language: English
• Subjects: Adaptive boosting; Artificial neural networks; Bayesian analysis; C band; C-bands; Campos Basin; Classification; Classification (of information); Classification algorithm; classification algorithms; Classifiers; Convolutional neural networks; Datasets; Decision trees; Deep learning; Image classification; Learning algorithms; Learning systems; Machine learning; Natural gas; Nearest neighbor search; Neural networks; oil rig classification; Oil spills; Oil-rigs; Radar imaging; Remote sensing; SAR; ship classification; Ships; Support vector machines; Synthetic aperture radar; Synthetic aperture radar images; Target Classification
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs14132966

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.