首页 > 论文 > 光学学报 > 35卷 > s1期(pp:110004--1)

高斯-瑞利混合模型在遥感图像分割中的应用

Application of Gaussian-Rayleigh Mixture Model in Remote Sensing Image Segmentation

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

在遥感图像的众多分割方法中,高斯混合模型(GMM)是一种常用的图像建模方法。提出了高斯-瑞利混合模型(GRMM)可能更适合对遥感图像建模。介绍了传统高斯混合模型和高斯-瑞利混合模型的区别。比较了这两种混合模型对图像建模的结果,并用数据说明高斯-瑞利混合模型拟合图像的像素分布误差更小。采用最大熵方法确定图像的最佳分类数,采用马尔可夫随机场(MRF)方法及新的势能函数完成图像的分割,采用迭代条件模型(ICM)完成分割过程中的最大后验概率计算问题。在实验中采用了3幅遥感图像,实验过程中比较了各个图像运用高斯混合模型和高斯-瑞利混合模型的分割和拟合结果,分别通过数据和分割结果体现了该分割方法的效果。

Abstract

Among the remote sensing images segmentation methods, Gaussian mixture model (GMM) is the widely used image model. Gaussian-Rayleigh mixture model (GRMM) is proposed, and it may be more suitable for remote sensing image modeling. The difference between classical GMM and GRMM is introduced. The modeling results of GMM and GRMM to the images are compared. The comparison data shows that the GRMM has less distribution errors than the GMM when modeling the images. The entropy-max method is utilized to determine the optimal class number. The Markov random field (MRF) and a new potential function is employed to segment the images. The iterative conditional model (ICM) is used to calculate the maximum posteriori probability. Three remote sensing images are utilized in the experiment, the fitting and segmentation results of GMM and GRMM are compared in the experiment process. The data and segmentation results show that the proposed method is more effective.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/aos201535.s110004

所属栏目:图像处理

基金项目:国家自然科学基金(60662003)、吉林省科技发展计划(20150414051GH)、吉林市科技计划(201362507)

收稿日期:2015-01-25

修改稿日期:2015-03-02

网络出版日期:--

作者单位    点击查看

侯一民:东北电力大学自动化工程学院, 吉林 吉林 132012
唐玥:东北电力大学自动化工程学院, 吉林 吉林 132012
孙晓雪:东北电力大学自动化工程学院, 吉林 吉林 132012
隋文秀:东北电力大学自动化工程学院, 吉林 吉林 132012

联系人作者:侯一民(ymh7821@163.com)

备注:侯一民(1978-),男,博士,副教授,主要从事图像处理与模式识别方面的研究。

【1】Hou Y, Yang y, Rao N, et al.. Mixture model and Markov Random field-based remote sensing image unsupervised clustering method[J]. Opto-Electronics Review, 2011, 19(1): 83-88.

【2】Fan Liheng, Lü Junwei, Deng Jiangsheng. Classification of hyperspectral remote sensing image based on bands grouping and classification ensembles[J]. Acta Optica Sinica, 2014, 34(9): 0910002.
樊利恒, 吕俊伟, 邓江生. 基于分类器集成的高光谱遥感图像分类方法[J]. 光学学报, 2014, 34(9): 0910002.

【3】Su W, Li J, Chen Y, et al.. Textural and local spatial statistics for the object goriented classification of urban areas using high resolution imagery[J]. International Journal of Remote Sensing, 2008, 29(11): 3105-3117.

【4】Xue Feng, Wang Runsheng. Road extraction by combined using statistical and structural information[J]. Acta Optica Sinica, 2001, 21(4): 504-508.
薛峰, 王润生. 组合利用统计和结构信息的道路提取算法[J]. 光学学报, 2001, 21(4): 504-508.

【5】Zhong P, Wang R. A multiple conditional Random fields ensemble model for urban area detection in remote sensing optical images[J]. Geoscience and Remote Sensing, IEEE Transactions on, 2007, 45(12): 3978-3988.

【6】Fan J, Han M, Wang J. Single point literative weighted fuzzy C-means clustering algorithm for remote sensing image segmentation[J]. Pattern Recognition, 2009, 42(11): 2527-2540.

【7】Mylonas S K, Stavrakoudis D G, Theocharis J B. GeneSIS: A GA-based fuzzy segmentation algorithm for remote sensing images[J]. Knowledge-Based Systems, 2013, 54(12): 86-102.

【8】Wan F, Deng F. Remote sensing image segmentation using mean shift method[J]. Simulation and Modeling Communications in Computer and Information Science, 2011, 176(11): 86-90.

【9】Pal M, Maxwell A E, Warner T A. Kernel-based extreme learning machine for remote-sensing image classification[J]. Remote Sensing Letters, 2013, 4(9): 853-862.

【10】Du Peijun, Chen Yu, Xia Junshi, et al.. A novel remote sensing image classification scheme based on data fusion, multiple features and ensemble learning[J]. Journal of Indian Soc Remote Sens, 2013, 41(2): 213-222.

【11】Nikou C, Galatsanos N P, Likas A C. A class-adaptive spatially variant mixture model for image segmentation[J]. Image Processing, IEEE Transactions on, 2007, 16(4): 1121-1130.

【12】Lunga D, Ersoy O. Kent mixture model for classification of remote sensing data on spherical manifolds[C]. Applied Imagery Pattern Recognition Workshop, IEEE, 2011: 1-7.

【13】Zhang Y, Brady M, Smith S. Segmentation of brain MR images through a hidden Markov Random field model and the expectation-maximization algorithm[J]. Medical Imaging, IEEE Transactions on, 2001, 20(1): 45-57.

【14】Deng H, Clausi D A. Unsupervised image segmentation using a simple MRF model with a new implementation scheme[J]. Pattern Recognition, 2004, 37(12): 2323-2335.

【15】Zhou S, Chen W, Jia F, et al.. Segmentation of brain magnetic resonance angiography images based on MAP-MRF with multi-pattern neighborhood system and approximation of regularization coefficient[J]. Medical Image Analysis, 2013, 17(8): 1220-1235.

【16】Seng C H, Bouzerdoum A, Amin M G, et al.. A Gaussian-Rayleigh mixture modeling approach for through-the-wall radar image segmentation[C]. Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, 2012: 877-880.

【17】Debes C, Amin M, Zoubir A. Target detection in singleand multiple-view through-the-wall radar imaging[J]. Geoscience and Remote Sensing, IEEE Transactions on, 2009, 47(5): 1349-1361.

【18】Tao W B, Tian J W, Liu J. Image segmentation by three-level thresholding based on maximum fuzzy entropy and genetic algorithm[J]. Pattern Recognition Letters, 2003, 24(16): 3069-3078.

【19】Vivone G, Addesso P, Conte R, et al.. A class of cloud detection algorithms based on a MAP-MRF approach in space and time[J]. Geoscience and Remote Sensing, IEEE Transactions on, 2014, 52(8): 5100-5114.

【20】Borges J, Bioucas-Dias J, Marcal A. Bayesian hyperspectral image segmentation with discriminative class learning[J]. Geoscience Remote Sensing, IEEE Transactions on, 2011, 49(6): 2151-2164.

【21】Zhang B, Li S, Jia X, et al.. Adaptive Markov random field approach for classification of hyperspectral imagery[J]. Geoscience Remote Sensing Letters, IEEE, 2011, 8(5): 973-977.

【22】Hegarat-Mascle S Le, Andre C. Use of Markov random fields for automatic cloud/shadow detection on high resolution optical images[J]. ISPRS J Photogramm Remote Sens, 2009, 64(4): 351-366.

引用该论文

Hou Yimin,Tang Yue,Sun Xiaoxue,Sui Wenxiu. Application of Gaussian-Rayleigh Mixture Model in Remote Sensing Image Segmentation[J]. Acta Optica Sinica, 2015, 35(s1): s110004

侯一民,唐玥,孙晓雪,隋文秀. 高斯-瑞利混合模型在遥感图像分割中的应用[J]. 光学学报, 2015, 35(s1): s110004

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF