期刊文献+

高分三号SAR精准海陆分割的混合策略方法 被引量:2

Hybrid strategy for precise sea-land segmentation in GF-3 SAR images
下载PDF
导出
摘要 高分三号(GF-3)是我国第一颗多极化雷达卫星,主要用于海洋遥感和海面监测,其中海陆分割是重要的预处理步骤.文章针对GF-3多极化合成孔径雷达(synthetic aperture radar,SAR)的精准海陆分割,提出了创新的混合策略方法,可提高分割性能对于相干斑噪声、风浪、成像等因素的稳健性.针对不同的极化通道采取三种不同的策略:1)对数混合高斯模型,用于确定海陆比,将纯陆地和纯海洋图像与海陆图像区分开,同时根据混合模型参数对海陆图像进行精细聚类;2)大津法,通过分别在对数域和复数域实现类间方差最大化,产生基于灰度信息的海陆掩膜;3)对数累积量,分析纹理信息,通过对数二阶矩与对数三阶矩之间的联系判断海陆大致分布,用作对投票机制产生的海陆掩膜进行验证与再分割,增强海陆分割精确性.针对大量GF-3数据进行实验,结果均达到理想效果,具备实际应用价值. Gaofen-3(GF-3)was the first multi-polarization radar satellite launched by China which is dedicated to marine monitoring and ocean remote sensing.Sea-land segmentation is a vital step of image preprocessing.In this paper,we propose a novel hybrid strategy for precise sea-land segmentation in GF-3 SAR images,which can improve the robustness of segmentation performance with respect to speckle noise,waves,imaging,and etc.Three different strategies are adopted in different polarized channels:1)logarithmic Gaussian mixture model(LGMM)is applied to distinguish all-land and all-sea images from mixture images by determining the ratio of sea-to-land,and it conducts fine clustering of sea-land segmentation according to the parameters of LGMM;2)OTSU method,which maximizes inter-class variance in logarithmic domain and complex domain respectively,and generates the sea-land masks based on gray information;3)logarithmic cumulants are adopted to analyze texture information,and judges the general distribution of mixture images by the connection between logarithmic second-order moment and logarithmic third-order moment,so as to verify and predict the sea-land masks generated by majority voting mechanism,and enhance the accuracy of sea-land segmentation.Experiments were carried out on a large number of GF-3 SAR images,and the results are exceptional.The proposed sea-land segmentation algorithm has potential practical application.
作者 侯晰月 徐丰 HOU Xiyue;XU Feng(Key Laboratory for Information Science of Electromagnetic Waves,MoE,Fudan University,Shanghai 200433,China)
出处 《电波科学学报》 EI CSCD 北大核心 2019年第6期798-805,共8页 Chinese Journal of Radio Science
基金 国家自然科学基金(61822107)
关键词 多极化SAR 海陆分割 对数混合高斯模型 大津法 对数累积量 polarimetric SAR sea-land segmentation logarithmic Gaussian mixture model OTSU method logarithmic cumulants
  • 相关文献

参考文献7

二级参考文献37

  • 1Dempster, A. P, Laird, N. M, Rubin, D. B. Maximum likelihood for incomplete data via the EM algorithm.[J] .J.R. Stat. Soc,1977,B, 39:1-38. 被引量:1
  • 2Liu C, Sun D X. Acceleration of EM Algorithm for Mixtures Models using ECME[J]. ASA Proceedings of the Stat. Comp. Session, 1997, 109-114. 被引量:1
  • 3Christophe Biemacki.Initializing EM Using the Properties of its Trajectories in Gaussian Mixtures [J]. Statistics and Computing,2004, 14, 3:267-279. 被引量:1
  • 4Patricia McKenzie, Michael Alder. Initializing the EM Algorithm for use in Gaussian Mixture Modelling [J]. Amsterdam Esevier Science BV, 1994:91-105. 被引量:1
  • 5Biernacki C, Celeux G, Govaert G. Choosing Starting Values for the EM Algorithm for Getting the Highest Likelihood in Multivariate Gaussian Mixture Models[J]. Computational Statistics and Data analysis, 2002. 被引量:1
  • 6Banfield J. D, Raftery A. E. Model-based Gaussian and non-Gaussian clustering [J]. Biometrics, 1993, 49:803-821. 被引量:1
  • 7Fraley C, A.E. Raftery.How many clusters? Which clustering method? -Answers via model-based cluster analysis [J]. The Computer Journal, 1998, 41:578-588. 被引量:1
  • 8D.W.Scott. On optimal and data-based histograms [J]. Biometrika, 1979, 66:605-610. 被引量:1
  • 9Fraley C.Algorithms for model-based Gaussian hierarchical clustering [J].SIAM J.Sci.Computer, 1999, 20:270-281. 被引量:1
  • 10AMIT S C, et al. Image Segmentation Methods: A Survey Ap- proach[C]//4th International ConferenceonCommunication Sys- tems and Network Technologies, 2014:929-933. 被引量:1

共引文献86

同被引文献11

引证文献2

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部