介绍了一种全新的区域影像分割技术--基于迎风格式偏微分方程（PDE）的Level Set方法进行海洋浮油膜特征提取.在该方法中,海洋浮油膜特征表示为扩散界面,影像灰度的梯度决定了界面扩散的方向和强度.界面边缘在影像灰度差异动力和曲率流的共同作用下不断向外扩散,能够有效地克服尖锐突起和裂缝等,在特征边缘趋于稳定和光滑.同时,该方法对高噪声具有一定抑制作用,适用于低对比度高噪声图像,特别是SAR图象中特征提取.以不同地区ERS-2 SAR图像中海洋浮油膜提取为例,进行方法验证,同时对传统的影像分割技术进行对比.

The special indications in Synthetic Aperture Radar images formed by oil slicks on ocean surface, which are seeped from hydrocarbon under sea bed, is important to search ocean oil and gas resources. This paper explores the segmentation of oil spills using a partial differential equation (PDE) level set method, which represents the oil slick surface as an implicit propagation interface. Specifically, the image intensity gradient is utilized as the impetus and direction for oil slick propagation. The integration of the intensity driven speed and curvature flow into the method allows the front interface to propagate naturally with topological changes, significant protrusions and narrow regions, giving rise to a stable and smooth boundary. In addition, it reduces the speckles simultaneously. The proposed method has been illustrated by experiments on oil slick segmentation using the ERS-2 SAR images. Its advantages over the traditional image segmentation approaches have also been demonstrated.