地球科学进展 ›› 2009, Vol. 24 ›› Issue (5): 555 -562. doi: 10.11867/j.issn.1001-8166.2009.05.0555

“土地利用/覆盖变化与综合减灾”专辑 上一篇    下一篇

支持向量机在遥感数据分类中的应用新进展
张睿 1,2,马建文 3   
  1. 1.中国科学院遥感应用研究所,北京  100101;  2.中国科学院研究生院,北京  100049;3.中国科学院对地观测与数字地球科学中心,北京  100190
  • 收稿日期:2008-12-31 修回日期:2009-04-01 出版日期:2009-05-10
  • 通讯作者: 张睿 E-mail:david.zhangrui@gmail.com
  • 基金资助:

    国家重点基础研究发展计划项目“陆表生态环境要素主被动遥感协同反演理论与方法”(编号:2007CB714406);中国高技术研究发展计划项目“卫星遥感SAR与光学影像自动配准与融合技术系统研究”(编号:2007AA12Z157);中国科学院知识创新工程青年人才领域前沿专项项目“多种地表覆盖条件下遥感邻近效应测量与校正方法研究”(编号:08S01100CX)资助.

State of the art on remotely sensed data classification based on support vector machines

Zhang Rui 1,2, Ma Jianwen 3   

  1. 1.Institute of Remote Sensing Applications, CAS, Beijing 100101, China;  2. Graduate University of CAS, Beijing 100049, China;
    3. Center for Earth Observation and Digital Earth, CAS, Beijing 100190, China
  • Received:2008-12-31 Revised:2009-04-01 Online:2009-05-10 Published:2009-05-10

      支持向量机是一种基于统计学习理论的新型机器学习算法,它通过解算最优化问题,在高维特征空间中寻找最优分类超平面,从而解决复杂数据的分类及回归问题。随着应用面的不断扩大,支持向量机在遥感领域也得到了广泛关注。该算法已经成功的应用于遥感数据的土地覆盖、土地利用分类,多时相遥感数据的变化检测,多源遥感数据信息融合等,并且在高光谱遥感数据处理中得到了广泛应用。综述了支持向量机算法在遥感数据分类中的应用。首先对支持向量机的理论进行简要介绍,进而综述了该算法在不同遥感问题中的应用进展,最后阐述了新型支持向量机算法的发展以及在遥感中的应用。

       Support Vector Machine (SVM) is a state-of-the-art machine learning algorithm based on statistical learning theory. It tries to find the optimal classification hyperplane in high dimensional feature space to handle complicated classification and regression problems by solving optimization problems. With the development of the theory and its applications, SVM has been used in remote sensing community successfully. SVM has been applied to land cover/land use classification for remotely sensed data, change detection for multi-temporal remote sensing data, and information fusion for multiple source data. Moreover, it has become a standard technique for hyperspectral data process. In this paper, the applications of SVM in remote sensing are reviewed. First, we introduced the basic theory of the SVM briefly. Then we reviewed the state of the art in different remote sensing applications. At last, we stated the development of several new SVM algorithms, which were derived from the SVM theory, and applications in remote sensing community.

中图分类号: 

[1] Vapnik V N. The Nature of Statistical Learning Theory\[M\]. New York: Springer-Verlag,1995.
[2] Hughes G. On the mean accuracy of statistical pattern recognizers[J].IEEE Transactions on Information Theory,1968,14(1):55-63.
[3] Vapnik V N. Statistical Learning Theory[M]. New York: Wiley,1998.
[4] Burges C J C. A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery,1998,2(2):121-167.
[5] Cristianini N,Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M]. Cambrideg: Cambridge University Press,2000.
[6] Mazzoni D, Garay M J, Davies R, et al. An operational MISR pixel classifier using support vector machines[J]. Remote Sensing of Environment, 2007,107(1/2):149-158.
[7] Mitra P, Shankar B U, Pal S K. Segmentation of multispectral remote sensing images using active support vector machines[J].Pattern Recognition Letters, 2004, 25(9):1 067-1 074.
[8] Song M J,Civco D. Road extraction using SVM and image segmentation[J].Photogrammetric Engineering and Remote Sensing, 2004, 70(12):1 365-1 371.
[9] Camps-Valls G, Gomez-Chova L, Munoz-Mari J, et al. Kernel-based framework for multitemporal and multisource remote sensing data classification and change detection[J].IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(6):1 822-1 835.
[10] Bovolo F, Bruzzone L, Marconcini M. A novel approach to unsupervised change detection based on a semisupervised SVM and a similarity measure[J].IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(7):2 070-2 082.
[11] Inglada J. Automatic recognition of man-made objects in high resolution optical remote sensing images by SVM classification of geometric image features[J].International Journal of Photogrammetry and Remote Sensing, 2007, 62(3):236-248.
[12] Brown M, Lewis H G, Gunn S R. Linear spectral mixture models and support vector machines for remote sensing[J].IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(5):2 346-2 360.
[13] Hsu C W,Lin C J. A comparison of methods for multiclass support vector machines[J].IEEE Transactions on Neural Networks, 2002, 13(2):415-425.
[14] Rifkin R,Klautau A. In defense of one-vs-all classification[J].Journal of Machine Learning Research, 2004, 5:101-141.
[15] Melgani F,Bruzzone L. Classification of hyperspectral remote sensing images with support vector machines[J].IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(8):1 778-1 790.
[16] Mathur A,Foody G M. Multiclass and binary SVM classification: Implications for training and classification users[J].IEEE Geoscience and Remote Sensing Letters, 2008, 5(2):241-245.
[17] Huang C, Davis L S, Townshend J R G. An assessment of support vector machines for land cover classification[J].International Journal of Remote Sensing, 2002, 23(4):725-749.
[18] Dixon B,Candade N. Multispectral landuse classification using neural networks and support vector machines: One or the other, or both?[J].International Journal of Remote Sensing, 2008, 29(4):1 185-1 206.
[19] Zhu G B,Blumberg D G. Classification using ASTER data and SVM algorithms; The case study of Beer Sheva, Israel[J].Remote Sensing of Environment, 2002, 80(2):233-240.
[20] Foody G M,Mathur A. A relative evaluation of multiclass image classification by support vector machines[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(6):1 335-1 343.
[21] Foody G M,Mathur A D. Toward intelligent training of supervised image classifications: Directing training data acquisition for SVM classification[J].Remote Sensing of Environment, 2004, 93(1/2):107-117.
[22] Foody G M,Mathur A. The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM[J].Remote Sensing of Environment, 2006, 103(2):179-189.
[23] Zhang L P, Huang X, Huang B, et al. A pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imagery[J].IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(10):2 950-2 961.
[24] Bruzzone L,Carlin L. A multilevel context-based system for classification of very high spatial resolution images[J].IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(9):2 587-2 600.
[25] Camps-Valls G, Gomez-Chova L, Calpe-Maravilla J, et al. Robust support vector method for hyperspectral data classification and knowledge discovery[J].IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(7):1 530-1 542.
[26] Camps-Valls G,Bruzzone L. Kernel-based methods for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(6):1 351-1 362.
[27] Zhang Youjing, Gao Yunxiao, Huang Hao, et al. Research on remote sensing classification of urban vegetation species based on SVM decision-making tree[J].Journal of remote sensing,2006,10(2):191-196.[张友静,高云霄,黄浩,等.基于SVM决策支持树的城市植被类型遥感分类研究[J]. 遥感学报,2006,10(2):191-196.]
[28] Xu Fang, Mei Wensheng, Zhang Zhihua. Least squares support vector machines for aerial images segmentation[J].Geomatics and Information Science of Wuhan University,2005,30(8):694-698.[徐芳,梅文胜,张志华. 航空影像分割的最小二乘支持向量机方法[J]. 武汉大学学报:信息科学版,2005,30(8):694-698.]
[29] Waske B,Benediktsson J A. Fusion of support vector machines for classification of multisensor data[J].IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12):3 858-3 866.
[30] Waske B,van der Linden S. Classifying multilevel imagery from SAR and optical sensors by decision fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(5):1 457-1 466.
[31] Dalponte M, Bruzzone L, Gianelle D. Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas[J].IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(5):1 416-1 427.
[32] Zhang Jinshui, He Chunyang, Pan Yaozhong, et al. The high spatial resolution RS image classification based on SVM method with the multi-source data[J].Journal of Remote Sensing, 2006, 10(1):49-57.[张锦水,何春阳,潘耀忠,等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J].遥感学报,2006, 10(1):49-57.]
[33] Huang Xin, Zhang Liangpei, Li Pingxiang. Classification of high spatial resolution remotely sensed imagery based upon fusion of multiscale features and SVM[J].Journal of Remote Sensing, 2007, 11(1):48-54.[黄昕,张良培,李平湘. 基于多尺度特征融合和支持向量机的高分辨率遥感影像分类[J]. 遥感学报,2007,11(1):48-54.]
[34] He Lingmin, Shen Zhangquan, Kong Fansheng,et al. Study on multi-source remote sensing images classification with SVM[J].Journal of Image and Graphics, 2007, 12(4):648-654.[何灵敏,沈掌泉,孔繁胜,等. SVM在多源遥感图像分类中的应用研究[J].中国图象图形学报,2007, 12(4):648-654.]
[35] Dash J, Mathur A, Foody G M, et al. Land cover classification using multi-temporal MERIS vegetation indices[J].International Journal of Remote Sensing, 2007,28(6):1 137-1 159.
[36] Huang C Q, Song K, Kim S, et al. Use of a dark object concept and support vector machines to automate forest cover change analysis[J].Remote Sensing of Environment,2008,112(3):970-985.
[37] Mantero P, Moser G, Serpico S B. Partially supervised classification of remote sensing images through SVM-based probability density estimation[J].IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3):559-570.
[38] Bruzzone L, Chi M M, Marconcini M. A novel transductive SVM for semisupervised classification of remote-sensing images[J].IEEE Transactions on Geoscience and Remote Sensing,2006, 44(11):3 363-3 373.
[39] Chi M M,Bruzzone L.Semisupervised classification of hyperspectral images by SVMs optimized in the primal[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(6):1 870-1 880.
[40] Demir B,Erturk S. Hyperspectral image classification using relevance vector machines[J].IEEE Geoscience and Remote Sensing Letters, 2007, 4(4):586-590.
[41] Foody G M. RVM-based multi-class classification of remotely sensed data[J].International Journal of Remote Sensing, 2008, 29(6):1 817-1 823.
[42] Munoz-Mari J, Bruzzone L, Camps-Valls G. A support vector domain description approach to supervised classification of remote sensing images[J].IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(8):2 683-2 692.
[43] Tax D M J,Duin R P W. Support vector domain description[J].Pattern Recognition Letters, 1999, 20(11/13):1 191-1 199.
[44] Foody G M, Mathur A, Sanchez-Hernandez C, et al. Training set size requirements for the classification of a specific class[J].Remote Sensing of Environment, 2006, 104(1):1-14.
[45] Tax D M J,Duin R P W. Support vector data description[J].Machine Learning, 2004, 54(1):45-66.
[46] Blanzieri E,Melgani F. Nearest neighbor classification of remote sensing images with the maximal margin principle[J].IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(6):1 804-1 811.
[47] Chen J, Wang C, Wang R S. Combining support vector machines with a pairwise decision tree[J].IEEE Geoscience and Remote Sensing Letters, 2008, 5(3):409-413.
[48] Ghoggali N,Melgani F. Genetic SVM approach to semisupervised multitemporal classification[J].IEEE Geoscience and Remote Sensing Letters, 2008, 5(2):212-216.
[49] Gomez-Chova L, Camps-Valls G, Munoz-Mari J, et al. Semisupervised image classification with Laplacian support vector machines[J].IEEE Geoscience and Remote Sensing Letters, 2008, 5(3):336-340.
[50] Zhang R,Ma J. An improved SVM method P-SVM for classification of remotely sensed data[J].International Journal of Remote Sensing,2008,29(20):6 029-6 036.

[1] 杨福强,陈科贵,黄长兵,陈愿愿,李进,马小林. PSO-LIBSVM在钾盐矿层识别中的应用研究[J]. 地球科学进展, 2019, 34(7): 757-764.
[2] 陈科贵, 吴刘磊, 陈愿愿, 王刚. 基于支持向量机的川中杂卤石分类识别研究[J]. 地球科学进展, 2016, 31(10): 1041-1046.
阅读次数
全文


摘要