Taravat Alireza, Oppelt Natascha
Remote Sensing & Environmental Modelling Lab, Kiel University, Kiel 24098, Germany.
Sensors (Basel). 2014 Dec 2;14(12):22798-810. doi: 10.3390/s141222798.
Oil spills represent a major threat to ocean ecosystems and their environmental status. Previous studies have shown that Synthetic Aperture Radar (SAR), as its recording is independent of clouds and weather, can be effectively used for the detection and classification of oil spills. Dark formation detection is the first and critical stage in oil-spill detection procedures. In this paper, a novel approach for automated dark-spot detection in SAR imagery is presented. A new approach from the combination of adaptive Weibull Multiplicative Model (WMM) and MultiLayer Perceptron (MLP) neural networks is proposed to differentiate between dark spots and the background. The results have been compared with the results of a model combining non-adaptive WMM and pulse coupled neural networks. The presented approach overcomes the non-adaptive WMM filter setting parameters by developing an adaptive WMM model which is a step ahead towards a full automatic dark spot detection. The proposed approach was tested on 60 ENVISAT and ERS2 images which contained dark spots. For the overall dataset, an average accuracy of 94.65% was obtained. Our experimental results demonstrate that the proposed approach is very robust and effective where the non-adaptive WMM & pulse coupled neural network (PCNN) model generates poor accuracies.
石油泄漏对海洋生态系统及其环境状况构成重大威胁。以往研究表明，合成孔径雷达（SAR）由于其记录不受云层和天气影响，可有效用于石油泄漏的检测和分类。暗区检测是石油泄漏检测过程中的首要关键阶段。本文提出了一种在SAR图像中自动检测暗点的新方法。提出了一种将自适应威布尔乘法模型（WMM）和多层感知器（MLP）神经网络相结合的新方法，用于区分暗点和背景。将结果与非自适应WMM和脉冲耦合神经网络相结合的模型结果进行了比较。所提出的方法通过开发自适应WMM模型克服了非自适应WMM滤波器设置参数的问题，朝着全自动暗点检测又迈进了一步。该方法在60幅包含暗点的ENVISAT和ERS2图像上进行了测试。对于整个数据集，平均准确率达到了94.65%。我们的实验结果表明，在所提出的方法中，非自适应WMM和脉冲耦合神经网络（PCNN）模型准确率较低时，该方法非常稳健且有效。
