多尺度水平集SAR影像水体自动分割方法

Automatic Water Segmentation Method in SAR Images Using Multi-scale Level Set

针对高分辨率SAR影像的水体特性,提出了一种新的可精确、快速、自动完成高分辨率SAR影像水体分割的方法。该方法将多尺度分析技术与水平集理论相结合,在考虑全局信息的同时,也顾及到了局部信息。同时,为了满足SAR图像的分布特性,将Gamma统计模型引入到水平集能量函数中,利用OTSU算法来初始化零水平集。为了消除SAR影像中疑似水体的目标,对分割结果进行了后处理。实验表明,该方法在提高精度的同时,也大大提高了水体提取的效率。

In order to extract water from SAR images automatically, accurately and quickly, a novel water segmentation algorithm combined multi-scale level set method with OTSU algorithm is proposed in this paper. Firstly, we introduced multi-scale framework into level set method, this technology considering both global information and local information of the image. Moreover, considering the speckle noise of SAR images, gamma model is defined for level set function, based on it, the segmentation result of OTSU algorithm is used to represent the initial segmentation curve. Finally, in order to eliminate the influence of farmland and road, post-processing is considered in this paper. The experiments with real SAR images demonstrate the effectiveness of the new method.