摘要
结合U分布对不同匀质性极化合成孔径雷达(PolSAR)数据的广泛建模能力及Potts马尔科夫随机场(MRF)模型对像素点之间类相关性的建模能力,提出了一种基于最大后验概率(MAP)准则的PolSAR图像无监督分类方法。利用迭代条件模式算法和Metropolis采样算法对像素点的类别进行更新,迭代过程中分布参数的估计采用基于梅林(Mellin)变换的矩阵对数累积量方法,以迭代过程中出现次数最多的类别最为像素点的最终分类结果。利用NASA/JPL实验室AIRSAR系统获取旧金山湾的PolSAR数据,对本文分类算法的有效性以及分布的杂波建模能力进行了仿真验证。实验结果表明,本文分类算法的精度优于Lee分类算法,分布对PolSAR数据的杂波建模准确性总体上优于复Wishart分布、K分布和G0分布。
The accurate classification of polarimetric synthetic aperture radar （PolSAR） images is a chal- lenging task because of the existence of the speckle noise resulting in many false alarms. By combining the capability of the distribution in fitting different clutter regions in the PolSAR image and the capability of the Potts Markov random fields of modeling the contextual class information between neighboring pix- els, a new unsupervised classification algorithm for PolSAR data is proposed based on maximum a poste- riori （MAP） criterion. Firstly,the conditional iterative mode algorithm and the Metropolis sampling algo- rithm are utilized to refresh the class type of each pixel by iteratively resolving the objective function which is established by the MAP classification criterion. Secondly, at each iteration step, to get more ac- curate classification result, the distribution parameters are estimated by using the method of matrix log- cumulants which is based on the Mellin transform. Finally, the final class type of each pixel is the one which appears most times in the iteration steps. The experiment utilizing an NASA/JPL/AIRSAR po- larimetric SAR image demonstrates that the proposed algorithm gets more accurate classification result than the Lee method,and the distribution fits the clutter of the PolSAR better than the Wishart distribu- tion,K distribution and Go distribution.
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2015年第4期788-796,共9页
Journal of Optoelectronics·Laser
