ALBERT

Description: Oil spills bring great damage to the environment and, in particular, to coastal ecosystems. The ability of identifying them accurately is important to prompt oil spill response. We propose a semi-automatic oil spill detection method, where texture analysis, machine learning, and adaptive thresholding are used to process X-band marine radar images. Coordinate transformation and noise reduction are first applied to the sampled radar images, coarse measurements of oil spills are then subjected to texture analysis and machine learning. To identify the loci of oil spills, a texture index calculated by four textural features of a grey level co-occurrence matrix is proposed. Machine learning methods, namely support vector machine, k-nearest neighbor, linear discriminant analysis, and ensemble learning are adopted to extract the coarse oil spill areas indicated by the texture index. Finally, fine measurements can be obtained by using adaptive thresholding on coarsely extracted oil spill areas. Fine measurements are insensitive to the results of coarse measurement. The proposed oil spill detection method was used on radar images that were sampled after an oil spill accident that occurred in the coastal region of Dalian, China on 21 July 2010. Using our processing method, thresholds do not have to be set manually and oil spills can be extracted semi-automatically. The extracted oil spills are accurate and consistent with visual interpretation.

Description: Polarimetric synthetic aperture radar is an important tool in the effective detection of marine oil spills. In this study, two cases of Radarsat-2 Fine mode quad-polarimetric synthetic aperture radar datasets are exploited to detect a well-known oil seep area that collected over the Gulf of Mexico using the same research area, sensor, and time. A novel oil spill detection scheme based on a multi-polarimetric features model matching method using spectral pan-similarity measure (SPM) is proposed. A multi-polarimetric features curve is generated based on optimal polarimetric features selected using Jeffreys–Matusita distance considering its ability to discriminate between thick and thin oil slicks and seawater. The SPM is used to search for and match homogeneous unlabeled pixels and assign them to a class with the highest similarity to their spectral vector size, spectral curve shape, and spectral information content. The superiority of the SPM for oil spill detection compared to traditional spectral similarity measures is demonstrated for the first time based on accuracy assessments and computational complexity analysis by comparing with four traditional spectral similarity measures, random forest (RF), support vector machine (SVM), and decision tree (DT). Experiment results indicate that the proposed method has better oil spill detection capability, with a higher average accuracy and kappa coefficient (1.5–7.9% and 1–25% higher, respectively) than the four traditional spectral similarity measures under the same computational complexity operations. Furthermore, in most cases, the proposed method produces valuable and acceptable results that are better than the RF, SVM, and DT in terms of accuracy and computational complexity.