基于分水岭分割和稀疏表示的高光谱图像分类方法

doi:10.11896/j.issn.1002-137X.2016.02.020

摘要/Abstract

摘要： 近年来,高光谱图像的分类受到了广泛的关注。许多机器学习的方法都在高光谱图像上得到了应用,如SVM、神经网络、决策树等。但光谱图像可能存在“同物异谱”和“同谱异物”的情况,这给高光谱图像的精确分类带来了一定挑战。针对该问题,提出了利用分水岭分割得到的空间信息与稀疏表示来得到更精确的分类结果。首先利用分水岭得到图像区域信息,然后以区域为单位,对每个区域的样本进行分类。在两幅图像上对该方法的有效性进行了验证,结果表明该方法优于其它一些同类方法。

关键词: 高光谱图像,稀疏表示,分类,分水岭

Abstract: In recent years,the classification has attracted wide attention.Many machine learning methods have been applied in hyperspectral image classification,such as SVM,neural network and decision tree.But in the hyperspectral image,different materials may have the same spectra and the same material in different locations may have different spectra,consequently bringing a challenge for accurate classification of hyperspectral image.So,we made use of the spatial information extracted from the watershed segementation and the sparse representation to get a more accurate classification results.Firstly,we extracted regional information from hyperspectral image by watershed segementation,then classificated all the samples in a region once.The effectiveness of our proposed method was evaluated via two images.And the results show that it exhibits state-of-the-art performance.

Key words: Hyperspectral image,Sparse representation,Classification,Watershed

舒速,杨明. 基于分水岭分割和稀疏表示的高光谱图像分类方法[J]. 计算机科学, 2016, 43(2): 89-94. https://doi.org/10.11896/j.issn.1002-137X.2016.02.020

SHU Su and YANG Ming. Hyperspectral Image Classification Method Based on Watershed Segmentation and Sparse Representation[J]. Computer Science, 2016, 43(2): 89-94. https://doi.org/10.11896/j.issn.1002-137X.2016.02.020

参考文献

[1] 常庆瑞,周勇,申光荣,等.遥感技术导论[M].北京:科学出版社,2004:1-8
[2] 童庆禧,张兵,郑兰芬.高光谱遥感——原理、技术与应用[M].北京:高等教育出版社,2006:38-46
[3] Chen Jin.On classification method of hyperspectral images[D].Changsha:National University of Defense Technology,2010(in Cinese) 陈进.高光谱图像分类方法研究[D].长沙:国防科技大学,2010
[4] David L.Hyperspectral image data analysis[J].IEEE SignalProcessing Magazine,2002,19(1):17-28
[5] Li Ma,Crawford M M,Tian Jin-wen.Local Manifold Learning-Based k-Nearest-Neighbor for Hyperspectral Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(11):4099-4109
[6] Goel P K,Prasher S O,Patel R M,et al.Classification of hyperspectral data by decision trees and artificial neural networks to indentify weed stress and nitrogen status of corn[J].Computers and Electronics in Agriculture,2003,39(2):67-93
[7] Zhou H,Mao Z,Wang D.Classification of coastal areas by airborne hyperspectral image[C]∥Proceedings of SPIE.2005,5832:471-476
[8] Landgrebe D A.Signal Theory Methods in Multispectral Re-mote Sensing[M].Wiley,New York,2003
[9] Chen C H,Ho P-G P.Statistical pattern recognition in remote sensing[J].Pattern Recongnition,2008,41(9):2731-2741
[10] Bali N,Mohammad-Djafari A.Bayesian approach with hiddenMarkov modeling and mean field approximation for hyperpectral data analysis[J].IEEE Transactions on Image Processing,2008,17(2):217-225
[11] Subramanian S,Gat N,Sheffield M,et al.Methodology for hyperspectral image classification using novel neural network[C]∥Proceedings of SPIE.1997,3071:128-137
[12] Yang F H,Meer F V D,Bakker W,et al.A back-propagationneural network for mineralogical mapping from AVIRIS data[J].International Journal of Remote Sensing,1999,20(1):97-110
[13] Hernández-Espinosa C,Fernández-Redondo M,Torres-Sospedra J.Some experiments with ensembles of neural networks for classification of hyperspectral images[C]∥International Symposium on Neural Networks(ISNN 2004).2004:912-917
[14] Pal M,Mather M.Support vector machines for classification in remote sensing[J].International Journal of Remote Sensing,2005,26(5):1007-1011
[15] Fauvel M,Benediktsson J A,Chanussot J,et al.Spectral andspatial classification of hyperspectral data using svms and morphological profiles[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(11):3804-3814
[16] Heikkinen V,Tokola T,Parkkinen J,et al.Simulated multispectral imagery for tree species classification using support vector machines[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(3):1355-1364
[17] Mountrakis G,Im J,Ogole C.Support vector machines in remote sensing:A review[J].ISPRS Journal of Photogrammetry and Remote Sensing,2011,66(3):247-259
[18] Camps-Valls G,Bruzzone L.Kernel-based methods for hyper-spectral image classification[J].IEEE Transactions on Geoscie-nce and Remote Sensing,2005,43(6):1351-1362
[19] Fauvel M,Chanussot J,Benediktsson J A.Evaluation of kernels for multiclass classification of hyperspectral remote sensing data[C]∥Proceedings of ICASSP.2006:813-816
[20] Guo B,Gunn S R,Damper R I,et al.Customizing kernel functions for SVM-based hyperspectral image classification[J].IEEE Transactions on Image Processing,2008,17(4):622-629
[21] Yang Shu-yuan,Qiao Yu,Yang Li-xia,et al.Hyperspectral Image Classification Based on Relaxed Clustering Assumption and Spatial Laplace Regularizer[J].IEEE Geoscience and Remote Sensing Letters,2014,11(5):901-905
[22] Kettig R L,Landgrebe D A.Classification of multispectral image data by extraction and classification of homogeneous objects[J].IEEE Transactions on Geoscience Electronics,1976,14(1):19-26
[23] Descombes X,Sigelle M,Preteux F.GMRF parameter estima-tion in a non-stationary framework by a renormalization technique:Application to remote sensing imaging[J].IEEE Transactions on Image Processing,1999,8(4):490-503
[24] Jia X,Richards J A.Managing the spectral-spatial mix in context classification using Markov random fields[J].IEEE Geoscience and Remote Sensing Letters,2008,5(2):311-314
[25] Song Ben-qin,Li Jun,Mura M D,et al.Remotely Sensed Image Classification Using Sparse Representations of Morphological Attribute Profiles[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(8):5122-5138
[26] Sun Le,Wu Ze-bin,Wei Zhi-hui,et al.Supervised Hyperspectral Image Classification Combining Sparse Unmixing and Spatial Constraint[C]∥Computer Vision in Remote Sensing (CVRS).2012:110-115
[27] Chen Yi,Nasrabadi N M,Tran T D.Hyperspectral Image Classification Using Dictionary-Based Sparse Representation[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(10):3973-3985
[28] Yuan Hao-liang,Lu Yang,Yang Li-na,et al.Sparse Representation Using Contextual Information for HyperSpectral Image Classfication[C]∥IEEE International Conference on Cyberne-tics(CYBCONF).2013:138-143
[29] Tang Yuan-yan,Yuan Hao-liang,Li Luo-qing.Manifold-BasedSparse Representation for Hyperspectral Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(12):7606-7618
[30] Tarabalka Y,Chanussot J,Benediktsson J A.Segmentation and classification of hyperspectral images using watershed transformation[J].Pattern Recognition,2010,43(7):2367-2379
[31] Wang Guo-quan,Zhou Xiao-hong,Yu Li-lei.Image Segmentation Based on Watershed Algorithm[J].Computer Simulation,2006,6(5):255-258(in Cinese) 王国权,周小红,蔚立磊.基于分水岭算法的图像分割方法研究[J].计算机仿真,2006,26(5):255-258
[32] Vincent L,Soille P.Watersheds in digital spaces:an efficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598
[33] Meyer F.Topographic distance and watershed lines[J].Signal Process,1994,38(1):113-125
[34] Stoev S.Rafsi—a fast watershed algorithm based on rainfalling simulation[C]∥Proceedings of the Eighth International Confe-rence on Computer Graphics,Visualization,and Interactive Digi-tal Media.2000:100-107
[35] Osma-Ruiz V,Godino-Llorente J I,Senz-Lechn N,et al.Animproved watershed algorithm based on efficient computation of shortest paths[J].Pattern Recognition,2007,40(3):1078-1090
[36] Camps-Valls G,Gomez-Chova L,Muoz-Marí J,et al.Composite Kernels for Hyperspectral Image Classification[J].IEEE Geoscience and Remote Sensing Letters,2006,3(1):93-97

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed