SVME: an ensemble of support vector machines for detecting oil spills from full resolution MODIS images

Abstract

This paper addresses oil spill detection from remotely sensed optical images. In particular, it focuses on the automatic classification of regions of interest (ROIs) in two classes, namely oil spills or look-alikes. Candidate regions and the corresponding boundaries have been manually identified from full resolution Moderate Resolution Imaging Spectroradiometer images, related to the Mediterranean Sea over the years 2008 and 2009. Then, a set of features has been extracted from each ROI, allowing to formulate the oil spill detection problem as a two-class classification task on the provided regions (i.e. using a supervised learning strategy). Since ROI classification is challenging, some desired characteristics for the classification algorithm are first identified, such as accuracy, robustness, etc. Then, a solution (called SVME) is provided: it is based on an ensemble of incremental/decremental cost-oriented Support Vector Machines, aggregated with the Receiving Operating Characteristic (ROC) convex hull method in the ROC space. Such a solution addresses all the desired characteristics. Finally, the results obtained on the collected dataset are shown. The importance of this study is the devising of a powerful classification technique that may have an impact on optical oil spill detection from space, especially if fused with satellite synthetic aperture radar data. Moreover, it is shown how the proposed system can be used as a decision support tool, to help a junior operator in making more reliable detections

Early Identification of Oil Spills in Satellite Images Using Deep CNNs

“…One key challenge that the researchers has to confront in classification models is the absence of a public dataset which may be utilized for benchmarking. In previous works [2,10,18] the required datasets were developed manually making relevant works almost non comparable. This constraint motivated us to develop a new dataset by collecting satellite SAR images of oil polluted areas via the European Space Agency (ESA) database, the Copernicus Open Access Hub 1 .…”

Automatic Mexico Gulf Oil Spill Detection from Radarsat-2 SAR Satellite Data Using Genetic Algorithm

“…Therefore, airborne remote sensing platforms, which include multispectral expert systems, hyperspectral airborne sensors, and airborne thermal infrared spectrometers, are also important. Each sensor exploits different physical properties of oil spill and its surrounding sea environment conditions (Cococcioni et al 2012.…”

Construction and Application of Marine Oil Spill Gravity Vector Differences Detection Model

“…It has become an important means of detecting oil spill. An optical remote sensing image based oil spill detection method is founded on the spectrum difference between seawater and the oil film and the oil film characteristics on the images such as band-combination and band-comparison detection [12][13], spectral analysis detection [14], SVM classification detection [15], etc.. However, the contrast of the oil slick and the water is often small, which reduces accuracy of the oil spill detection.…”