欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
提出了一种多视极化合成孔径雷达（PolSAR）图像的迭代分类方法。首先利用极化G0分布描述多视极化协方差矩阵的统计特性，并进行初始的最大似然分类，然后利用马尔可夫随机场（MRF）估计像素类标号的先验概率，最后根据MAP（最大后验概率）准则对PolSAR图像进行分类。整个分类流程迭代进行。分类结果表明该方法精度高，收敛速度快。利用NASA／JPL获取的4视AIRSAR实测数据验证了本文方法的有效性。
英文摘要：
An iterative classification scheme of multi - look polarimetric synthetic aperture radar（PolSAR） images is presented here. Firstly. the polarimetric GO distribution is employed to describe the statistical characteristics of polarimetric covariance matrices. Then, an initial classification is provided by the maximum-likelihood classifier. Next, the Markov random field（MRF） is used to estimate the prior probabilities of class labels of pixels. Finally, the method classifies PolSAR images according to the MAP （maximum a posteriori ） criterion. The whole classification procedure is implemented iteratively. The classification results show that the method has high performance in accuracy and convergence. Experimental results using NASA/JPL 4-look AIRSAR data demonstrate the effectiveness of the proposed method.
同期刊论文项目
同项目期刊论文
期刊信息
位置：