高斯Copula的多光谱遥感影像分割

doi:10.16451/j.cnki.issn1003-6059.201907007

摘要
图/表
参考文献(0)
相关文章 (3)

全文: PDF (1990 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

为了充分利用多光谱影像波段间的相关性,提出高斯Copula的多光谱遥感影像分割方法.首先,建立基于马尔可夫随机场的标号场模型,使用Potts模型刻画该标号场.然后,建立表征像素光谱测度的特征场,利用高斯Copula建立像素光谱测度的多变量统计模型以刻画该特征场.结合标号场、特征场模型及各模型参数的先验概率,利用贝叶斯定理建立多光谱影像分割的后验概率模型.最后,设计适用于模拟后验概率模型的M-H算法,在最大后验概率策略下获取最优分割结果.对模拟和真实多光谱影像分割结果表明,文中方法描述波段间相关性的能力较强,准确性较高.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	赵泉华
	赵静
	张洪云
	李玉

关键词 ：高斯Copula, 遥感影像分割, 马尔可夫随机场(MRF), Metropolis-Hastings(M-H)算法

Abstract：

To take full advantage of inter-band correlations of multispectral remote sensing images, a multispectral remote sensing image segmentation method based on Gaussian copula function is proposed. Firstly, the Markov random field model is exploited to establish a label field and the label field is characterized by the Potts model. Then, the feature field characterizing pixel spectral measurements is built. A multivariate statistical model based on Gaussian copula modeling pixel spectral measurement is proposed. Furthermore, a posterior probability model of multispectral remote sensing image segmentation is established by Bayes theorem combined with the label field model, the feature field model and the prior probabilities of model parameters. The Metropolis-Hastings algorithm is designed to simulate the posterior probability model, and the optimal segmentation is obtained under the maximum a posterior strategy. Experiments are carried out with simulated and real multispectral images respectively, and experimental results indicate that the proposed algorithm has a strong ability to describe the correlation between bands with a high accuracy.

Key words： Gaussian Copula Remote Sensing Image Segmentation Markov Random Field(MRF) Metropolis-Hastings(M-H) algorithm

收稿日期: 2019-03-05

ZTFLH:

TP 391

基金资助:

国家自然科学青年科学基金项目(No.41301479)、辽宁省高校创新人才支持计划项目(No.LR2016061)、辽宁省教育厅科学技术研究一般项目(No.LJCL009)资助

作者简介: 赵泉华(通讯作者),博士,教授,主要研究方向为遥感图像建模与分析、随机几何在遥感图像处理中的应用.E-mail:zqhlby@163.com.赵静,硕士研究生,主要研究方向为遥感影像处理.E-mail:1505561475@qq.com.张洪云,博士研究生,主要研究方向为数字图像处理.E-mail:zhanghongyun0310@163. com.李玉,博士,教授,主要研究方向为遥感数据处理理论与应用基础研究.E-mail:lntuliyu@163.com.

引用本文:

赵泉华,赵静,张洪云,李玉. 高斯Copula的多光谱遥感影像分割[J]. 模式识别与人工智能, 2019, 32(7): 633-641. ZHAO Quanhua, ZHAO Jing, ZHANG Hongyun, LI Yu. Multispectral Remote Sensing Image Segmentation Using Gaussian Copula. , 2019, 32(7): 633-641.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201907007 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2019/V32/I7/633

[1] LIU T T, ZHANG L P, LI P X, et al. Region Segmentation of Multi-spectral Remote Sensing Image Using Improved JSEG Algorithm. Journal of Remote Sensing, 2009, 13(1): 30-34.
[2] 高国勇.改进的模糊聚类遥感影像分割.测绘与空间地理信息, 2015, 38(6): 98-100.
(GAO G Y. Improved Fuzzy Clustering Image Segmentation Algorithm for Remote Sensing Images. Geomatics & Spatial Information Technology, 2015, 38(6): 98-100.)
[3] 祖成玉.基于邻域统计特征MRF的图像分割算法.硕士学位论文.大连:大连海事大学, 2018.
(ZU C Y. Image Segmentation Algorithm Based on Neighborhood Statistics MRF. Master Dissertation. Dalian, China: Dalian Maritime University, 2008.)
[4] 马龙,王鲁平,沈振康.基于MRF的复杂背景下缓动目标分割方法.信号处理, 2010, 26(6): 911-916.
(MA L, WANG L P, SHEN Z K. A Slow-Moving-Object Segmentation Technology Based on MRF under Complex Background. Journal of Signal Processing, 2010, 26(6): 911-916.)
[5] COMER M, BOUMAN C A, DE GRAEF M, et al. Bayesian Me-thods for Image Segmentation. Journal of the Minerals, Metals and Materials Society, 2011, 63(7): 55-57.
[6] 田杰,韩冬,胡秋霞,等.基于PCA和高斯混合模型的小麦病害彩色图像分割.农业机械学报, 2014, 45(7): 267-271.
(TIAN J, HAN D, HU Q X, et al. Segmentation of Wheat Rust Lesion Image Using PCA and Gaussian Mix Model. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(7): 267-271.)
[7] WANG Y, ZHAO Q H, LI Y. Voronoi Tessellation Based Regionalised Segmentation for Colour Texture Image. IET Computer Vision, 2017, 10(7): 613-622.
[8] 王红莲.连接函数(Copula)理论及其在金融中的应用.硕士学位论文.上海:上海财经大学, 2006.
(WANG H L. Copula Theory and Its Application in Financial Field. Master Dissertation. Shanghai, China: Shanghai University of Finance and Economics, 2006.)
[9] LI D X. On Default Correlation: A Copula Function Approach. Journal of Fixed Income[C/OL]. [2019-02-15]. screpey.free.fr/doc/LIdefcorr.pdf.
[10] ZHANG M M, BEDFORD T. Vine Copula Approximation: A Generic Method for Coping with Conditional Dependence. Statistics and Computing, 2018, 28(1): 219-237.
[11] ELFADALY F G, GARTHWAITE P H. Eliciting Dirichlet and Gau-ssian Copula Prior Distributions for Multinomial Models. Statistics and Computing, 2017, 27(2): 449-469.
[12] BRUNEL N, PIECZYNSKI W, DERRODE S. Copulas in Vectorial Hidden Markov Chains for Multicomponent Image Segmentation // Proc of the IEEE International Conference on Acoustics, Speech, and Signal Processing. Washington, USA: IEEE, 2005: 717-720.
[13] FLITTI F, COLLET C, JOANNIC-CHARDIN A. Unsupervised Multiband Image Segmentation Using Hidden Markov Quadtree and Copulas // Proc of the IEEE International Conference on Image Processing. Washington, USA: IEEE, 2011: 634-637.
[14] 胡俊迎.基于RJMCMC的Gamma分布尺度参数的多变点检测. 硕士学位论文.合肥:合肥工业大学, 2017.
(HU J Y. Multiple Change-Point Detection for the Scale Parameter in Gamma Distribution Based on RJMCMC. Master Dissertation. Hefei, China: Hefei University of Technology, 2017.)
[15] 孙立晔,韩军伟,胡新韬,等.基于Markov随机场理论的鼠脑切片显微图像的分割研究.模式识别与人工智能, 2013, 26(5): 498-503.
(SUN L Y, HAN J W, HU X T, et al. Cell Segmentation in Microscopic Images of Mice Brain Based on Markov Field Theory. Pattern Recognition and Artificial Intelligence, 2013, 26(5): 498-503.)
[16] GEMAN S, GEMAN D. Stochastic Relaxation, Gibbs Distribution, and Bayesian Restoration of Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, 6(6): 721-741.
[17] CHIB S, GREENBERG E. Understanding the Metropolis-Hastings Algorithm. The American Statistician, 1995, 49(4): 327-335.
[18] BRUNEL N J B, LAPUYADE-LAHORGUE J, PIECZYNSKI W. Modeling and Unsupervised Classification of Multivariate Hidden Markov Chains with Copulas. IEEE Transactions on Automatic Control, 2011, 55(2): 338-349.
[19] NELSEN R B. An Introduction to Copulas. New York, USA: Spring-Verlag, 1999.
[20] 盛世明.基于连接函数的VaR的蒙特卡洛算法.统计与决策, 2010(21): 27-29.
(SHENG S M. Monte Carlo Algorithm Based on VaR of Copula. Statistics and Decision, 2010(21): 27-29.)
[21] 朱慧明,李荣,曾昭法,等.基于M-H抽样算法的贝叶斯Probit分位回归模型研究.湖南大学学报(自然科学版), 2013, 40(2): 98-102.
(ZHU H M, LI R, ZENG Z F, et al. Bayesian Analysis of Probit Quantile Regression Models Based on Metropolis-Hastings Algorithm. Journal of Hunan University(Natural Sciences), 2013, 40(2): 98-102.)