Please wait a minute...
img

Wechat

Remote Sensing Technology and Application  2009, Vol. 24 Issue (2): 132-139    DOI: 10.11873/j.issn.1004-0323.2009.2.132
    
A HMGMRF Model and Its Application inHigh-resolution Imagery Segmentation
SUN Xiao-dan 1,2,XU Han-qiu 1
(1.College of Environment and Resources,Key Laboratory of Spatial Data Mining and
Information Sharing,State Ministry of Education,Fuzhou University,Fuzhou 350108,China;2.Fuzhou Vocational &|Technical College,Fuzhou 350108,China)
Download:  PDF (878KB) 
Export:  BibTeX | EndNote (RIS)      
Abstract  

In this paper a Hierarchical Multispectral Gauss Markov Random Field (HMGMRF) model and its corresponding segmentation algorithm are proposed by modifying approach of anticipation dispersion of Gauss Markov Random Field (GMRF).In the segmentation procedure,the HMGMRF model is first used to analyze variational tendency of each land-cover classes in multispectral bands (i.e.multispectral texture characters of land-cover classes),neighborhood space is extended from single layer to multi-layer by introducing correlations of the spectral bands of remote sensing imagery,dimension of texture character is extended,thus capability to describe texture characters of the model is improved.Then,based on Bayesian principle,Expectation Maximization algorithm is accompanied by the estimation of model parameter on each land-cover classes.Finally,based on intensity texture characters,Maximum a posteriori is employed to perform image segmentation.Experimental results show that the proposed HMGMRF model-based segmentation algorithm is more capable in differentiating land cover classes and thus can achieve higher segmentation accuracy.

Key words:  High-resolution imagery      Spectral correlation      HMGMRF model      Segmentation algorithm     
Received:  09 November 2008      Published:  29 February 2012
TP 391  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
SUN Xiao-dan
XU Han-qiu

Cite this article: 

SUN Xiao-dan,XU Han-qiu. A HMGMRF Model and Its Application inHigh-resolution Imagery Segmentation. Remote Sensing Technology and Application, 2009, 24(2): 132-139.

URL: 

http://www.rsta.ac.cn/EN/10.11873/j.issn.1004-0323.2009.2.132     OR     http://www.rsta.ac.cn/EN/Y2009/V24/I2/132

<[1] Boykov Y,Veksler O,Zabih R.Fast Approximate Energy Mi-nimization Via Graph Cuts[C].Proceedings of the Seventh IEEE International Conference on Computer Vision,1999:377-384.

[2]〖KG*5/6〗Li S Z.Markov Random Field Modeling in Image Analysis[M].Tokyo:Springer-Verlag,2001:8-26.

[3] Hideki N,Shirazi M N,Kawaguchi E.MRF-based Texture Classification Using Wavelet Decomposed Images[J].Pattern Recognition,2002,35(4):771-782.

[4] Liu Guodong,Ye Maodong.Texture Segmentation Based on Wavelet-double Markov Rand Fields[J].Journal of Zhejiang University(Science Edition),2006,33(2):149-155.[刘国栋,叶懋冬.基于小波—双马尔可夫随机场的纹理分类[J].浙江大学学报(理学版),2006,33(2):149-155.]

[5] Panjwani D K,Healey G.Markov Random Field Models for Unsupervised Segmentation of Textured Color Images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(10):939-954.

[6] Tseng D C,Lai C C.A Genetic Algorithm for MRF-based Segmentation of Multispectral Textured Images[J].Pattern Recognition Letters,1999,20(14):1499-1510.

[7] Zhao Yindi,Zhang Liangpei,Li Pingxiang.Universal Markov Random Fields and Its Application in Multispectral Textured Image Classification[J].Journal of Remote Sensing,2006,10(1):123-129.[赵银娣,张良培,李平湘.广义马尔可夫随机场及其在多光谱影像分类中的应用[J].遥感学报,2006,10(1):123-129.]

[8] Manduchi R.Mixture Models and the Segmentation of Multimodal Textures[C].Proceeding IEEE Computer Vision and Pattern Recognition(1).Hilton Head Island:[s.n],2000:98-104.

[9] Yu Peng,Zhang Zhenlong,Hou Zhiqun.Textured Image Segmentation Based on Gauss Markov Random Field Mixture Model[J].Acta Geodaetica et Cartographica Sinica,2006,35(3):224-228.[余鹏,张震龙,侯智群.基于高斯马尔可夫随机场混合模型的纹理影像分类[J].测绘学报,2006,35(3):224-228.]

[10] Kato Z.Segmentation of Color Images Via Reversible Jump MCMC Sampling[J].Image and Vision Computing,2008,26(3):361-371.

[11] Liu Xiaoyun,Liao Zhiwu,Wang Zhensong,et al.Gaussian Mixture Models Clustering Using Markov Random Field for Multispectral Remote Sensing Images[C].Proceedings of the Fifth International Conference on Machine Learning and Cybernetics,Dalian,13-16 August 2006.

[12] Deng H,Clausi D A.Gaussian MRF Rotation-Invariant Feature for Image Classification[C].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,28(7):951-955.

[13] Rellier G,Descombes X,Falzon F.Texture Feature Analysis Using a Gauss-Markov Model in Hyperspectral Image Classification[C].IEEE Transactions on Geoscience and Remote Sensing,2004,42(7):1543-1551.

[14] Jensen J R.Introductory Digital Image Processing A Remote Sensing Perspective[M].Beijing:China Machine Press,2007:127-134.

[15] Kato Z,Pong T C.A Markov Random Field Image Segmentation Model for Color Textured Images[J].Image and Vision Computing,2006,24(10):1103-1114.

[16] Xu Hanqiu.Remote Sensing Information Extraction of Urban Built-up Land Based on a Data-dimension Compression Technique[J].Journal of Image and Graphics,2005,10(2):223-229.[徐涵秋.基于压缩数据维的城市建筑用地遥感信息提取[J].中国图象图形学报,2005,10(2):223-229.]
No Suggested Reading articles found!