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

Abstract

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.

Hybrid feature extraction based on PCA and CNN for oil rig classification in C-Band SAR imagery

“…4. BOOTSTRAP: to increase the number of samples to be analyzed by the classifiers, 50 subgroups are generated randomly and with replacement, based on the df-16vh data set and following the methodology applied by; 3,16 5. TRAIN AND TEST: each subgroup is divided into training samples (80% of the total samples) and test samples (20% of the total samples);…”

“…12 Another approach using CNN for feature extraction and SVM as a classification algorithm is presented by. 13 Recently, 3 showed that ML techniques are efficient for ATR of maritime targets in polarimetric SAR images. For that, authors considered the VGG16 and VGG19 CNNs to extract the representative features from the SAR image.…”

Marine Infrastructure Detection with Satellite Data—A Review

“…Especially since 2019, the interest in observing aquaculture has increased enormously. The second most frequently investigated topic is the platforms [14,17,29,30,36,38,43,[94][95][96][97][98][99][100][101][102][103][104][105][106], which have been the subject of continuous interest since 2012 when Casadio et al observed this type in the North Sea by their characterization of night-time gas flaring [101]. Since then, 20 studies were published detecting platforms offshore.…”

“…The fields of application and infrastructures detected with radar data are diverse. Of the total of 32 reviewed articles (35%), aquaculture was identified in 11 [39,49,50,59,62,67,68,70,93,114,115], platforms in 18 [14,17,38,43,[95][96][97][98][99][100][101][104][105][106], OWFs in five [41,42,51,107,108], and bridges in 2 [44,45]. The one study that used hyperspectral satellite data used them to detect aquaculture [64].…”

Improvement of Lithological Mapping Using Discrete Wavelet Transformation from Sentinel-1 SAR Data

“…With the development of artificial intelligence, the classification ability of classifiers has gradually improved. Recently, deep learning has been commonly used to improve the classification accuracy of remote sensing data [18,19]. Deep-learning algorithms require a large number of training samples, and many studies do not investigate the sample points in the field but select samples directly based on geological maps.…”