摘要
综合SAR(synthetic aperture radar)影像的统计模型假设与k-means聚类算法,提出了一种结合水体分布先验概率估计的水体概率估计方法。首先,用贝叶斯推断对研究区域后向散射系数做统计模型假设。随后,结合聚类算法对像元作分类,估计水体分布先验概率,结合统计分布直方图使用非线性最小二乘拟合完成模型参数估计。试验选取了高分三号(GF-3)多种工作模式数据,并用高分一号(GF-1)影像进行验证。结果表明,该方法可有效实现SAR影像的高精度水体概率估计。
We combine k-means cluster algorithm with the statistical model of SAR(synthetic aperture radar) images and develop the probabilistic water body mapping algorithm based on the priori probability estimation.Firstly, we make the statistical model assumption about backscatter values based on Bayesian theory.Then, we classify the images based on cluster algorithm, calculate the prior probability of the water body mapping and estimate the parameters of the statistical model of water distribution.Thewater body probabilistic maps based on GF-3 images in Luquan and Xianning are calculated and then validated with GF-1 images.The algorithm is effective on high-precision probabilistic water body mapping of SAR images.
作者
孟令奎
毛旭东
魏祖帅
张文
MENG Lingkui;MAO Xudong;WEI Zushuai;ZHANG Wen(School of Remote Sensing and Information Engineering, Wuhan University,Wuhan430079, China;Collaborative Innovation Center of Geospatial Technology, Wuhan430079, China)
出处
《测绘学报》
EI
CSCD
北大核心
2019年第4期439-447,共9页
Acta Geodaetica et Cartographica Sinica
基金
国家重点研发计划(2017YFC0405806)~~
