基于SWT域改进粒子滤波的SAR图像降斑算法

摘要

The particle filter (PF) algorithm has been successfully applied to synthetic aperture radar (SAR) image despeck ling. In this paper, we propose a modified PF despeckling algorithm based on Markov random field ( MRF) in stationary wavelet do main . It is shown that the wavelet coefficients of SAR images which exhibit significantly non-Gaussian statistics can be described ac curately by generalized Gaussian distribution (GGD) in stationary wavelet domain. MRF is introduced to redefine the weight of the particles to amend the weight deviation.Furthermore,the sampling interval is updated according to the new weight.To enhance the efficiency of the proposed algorithm,region-divided processing is implemented.Experiment results and analysis demonstrate the as cendant performance of the proposed algorithm in noise reduction, preservation of the textural features, single target and edges of SAR images.%粒子滤波(PF)非常适合处理非高斯状态空间模型的滤波问题,而SAR图像的非高斯降斑算法正是粒子滤波的一个有效应用,本文在平稳小波变换(SWT)域上提出了一种基于马尔可夫随机场(MRF)的改进PF的SAR图像降斑算法.新算法首先分析验证了SAR图像在SWT域比在DWT域中利用广义高斯分布(GGD)建模更为精确;然后针对基本PF降斑算法中的粒子整体权重偏差问题,引入MRF重新定义粒子权重,并通过权重更新粒子的采样区间以优化粒子分布;最后为了提高本文降斑算法的实时性,依据小波系数的局部统计特性把图像分为平滑和边缘进行分区域处理.本文针对模拟SAR图像和实测SAR图像进行了仿真,仿真结果和分析表明降斑后的图像能够在去除噪声的同时较好的保持图像的边缘和纹理结构特征,而且分区域处理有效地提高了算法的效率.