一种基于G^0分布的水平集SAR图像分割方法  

A Level Set Approach for SAR Image Segmentation Based on G^0 Distribution

作　　者：冯籍澜[1] 曹宗杰[1] 皮亦鸣[1] 

机构地区：[1]电子科技大学电子工程学院,成都611731

出　　处：《现代雷达》2010年第12期35-39,共5页Modern Radar

基　　金：国家自然科学基金资助项目(60802065;60772143)

摘　　要：G0分布是一种性能优良的概率统计模型,能够精确描述SAR图像中均匀区域、不均匀区域以及极不均匀区域的统计特性。文中基于G0分布提出了一种基于概率统计模型的变分水平集SAR图像分割方法。该方法通过引入G0分布统计模型,定义了一种更加适用于SAR图像分割的能量泛函。利用基于Mellin变换的G0分布的参数估计方法估计各个区域内最优的分布参数,并且通过水平集方法进行偏微分方程的数值求解,实现了SAR图像的区域和目标分割。由于G0分布的采用,使得该方法能够适用于多种SAR图像的分割。利用模拟和真实SAR图像上的分割实验验证了该方法的有效性。The G0 distribution has outstanding performance to accurately describe the statistical properties of extremely heterogeneous areas as well as heterogeneous and homogeneous areas in SAR images.In this paper,a variational level set approach that is based on the G0 distribution is proposed for SAR image segmentation problem.By introducing G0 distribution,a new energy functional that is applicable for SAR image segmentation is defined.To implement the segmentation of the SAR image,the parameters of the G0 distribution are estimated by the methods based on Mellin transform,and level set function is applied for the numerical solution of PDEs which are derived from the minimization of the energy function.The experiments based on both synthetic and real SAR images prove that the proposed algorithm is applicable for a series of SAR images with different scenes since the introduction of G0 distribution.

关 键 词：SAR图像 分割 变分水平集 G0分布 

分 类 号：TN957.52[电子电信—信号与信息处理]