Classification of Ocean Surface Slicks in Simulated Hybrid-Polarimetric SAR Data

Abstract

In this paper, we consider hybrid-polarimetric synthetic aperture radar (SAR) data of ocean surface slicks, and hypothesize that we can design a system that is able to discriminate between mineral oil, plant oil, and clean sea. We focus particularly on challenges related to data set shift between the training and test data. In SAR images of ocean surfaces, data set shift is typically caused by the variation of wind level and incident angles that directly impact the backscatter intensities. We evaluate several classifiers, domain adaptation strategies, and multilooking strategies. Hybrid-polarimetric SAR data are simulated from the Radarsat-2 quad-pol images. The proposed methodology was trained using five different Radarsat-2 quad-pol images that cover slicks of known types, and tested on 10 different Radarsat-2 quad-pol images covering various ocean surface slicks. The results show that we were able, to a large degree, to classify the type of various surface slicks. The average classification accuracy obtained from cross-validation on the training data was 91%. The results also show that we were able to correctly classify surface slick in new test images, even if the wind, surface, and acquisition conditions were different from the training images. We conclude that hybrid polarity is an attractive mode for future enhanced SAR-based oil spill monitoring; however, to fully exploit the imaging mode, single-look complex images are necessary.