On the Empirical-Statistical Modeling of SAR Images With Generalized Gamma Distribution
On the Empirical-Statistical Modeling of SAR Images With Generalized Gamma Distribution
复制标题
广义伽马分布SAR图像经验统计建模
DOI：
10.1109/jstsp.2011.2138675
复制
发表时间：
2011-06-01
影响因子：
7.5
通讯作者：
Fan, Ping-Zhi
中科院分区：
文献类型：
--
作者：
Li, Heng-Chao;Hong, Wen;Fan, Ping-Zhi
本文提出了一种用于合成孔径雷达（SAR）图像经验建模的有效统计模型--广义Gamma分布（G Gamma D）。G Gamma D形成了大量的替代分布（特别是包括瑞利，指数，Nakagami，Gamma，威布尔和对数正态分布通常用于SAR图像的概率密度函数（pdf）作为特殊情况），并灵活地模拟具有不同土地覆盖类型的SAR图像。基于第二类累积量，利用Polygamma函数的二阶逼近，得到了GGamma D参数的封闭估计。由于不涉及数值迭代求解过程，该估计器计算效率高，因此可以使G Gamma D方便地应用于在线SAR图像处理。最后，从实际的SAR图像进行测试的实验结果表明，G伽马D可以实现更好的拟合优度比国家的最先进的PDF。
In this paper, an efficient statistical model, called generalized Gamma distribution (G Gamma D), for the empirical modeling of synthetic aperture radar (SAR) images is proposed. The G Gamma D forms a large variety of alternative distributions (especially including Rayleigh, exponential, Nakagami, Gamma, Weibull, and log-normal distributions commonly used for the probability density function (pdf) of SAR images as special cases), and is flexible to model the SAR images with different land-cover typologies. Moreover, based on second-kind cumulants, a closed-form estimator for G Gamma D parameters is derived by exploiting the second-order approximation for Polygamma function. Without involving the numerical iterative process for solutions, this estimator is computationally efficient and, hence, can make the G Gamma D convenient for applications in the online SAR image processing. Finally, experimental results from tests carried out with actual SAR images demonstrate that the G Gamma D can achieve better goodness of fit than the state-of-the-art pdfs.