WANG Kai, SHU Ning, KONG Xiangbing, LI Liang. A Multi-feature Conversion Adaptive Classification of Hyperspectral Image[J]. Geomatics and Information Science of Wuhan University, 2015, 40(5): 612-616. DOI: 10.13203/j.whugis20130384
Citation: WANG Kai, SHU Ning, KONG Xiangbing, LI Liang. A Multi-feature Conversion Adaptive Classification of Hyperspectral Image[J]. Geomatics and Information Science of Wuhan University, 2015, 40(5): 612-616. DOI: 10.13203/j.whugis20130384

A Multi-feature Conversion Adaptive Classification of Hyperspectral Image

Funds: The National 863Program of China,No.2013AA102401;Fundamental Research Funds for the Central Universities,
More Information
  • Author Bio:

    WANG Kai: 国家863计划资助项目(2013AA102401);中央高校基本科研业务费专项资金资助项目(201121302020007);黄河水利科学研究院科技发展基金资助项目(黄科发201301)

  • Received Date: August 05, 2013
  • Revised Date: May 04, 2015
  • Published Date: May 04, 2015
  • Spectral similarity measure is an important tool of hyperspectral remote sensing image clas-sification.By setting the threshold to judge the pixel spectrum and the reference spectra is similar ordissimilar.To overcome this problem,this paper proposes a multi-feature conversion adaptive classifi-cation of hyperspectral image,this is done through using spectral similarity measure value as similari-ty patterns.Experimental results show that the proposed methods are,compared with the traditionalSVM method in the overall accuracy of classification,increased by 6.25%and 8.72%,also it impliesthat using simple learnable measures outperforms complex and manually turned techniques used in tra-ditional classification.
  • [1]
    Zhang Liangpei,Zhang Lifu.Hyperspectral RemoteSensing[M].Wuhan:Wuhan University Press,2005(张良培,张立福.高光谱遥感[M],武汉:武汉大学出版社,2005)[2] van der Meer F.The Effectiveness of Spectral Simi-larity Measures for the Anaysis of HyperspectralImagery[J].Int J Appl Earth Obs,2006,8(1):3-17[3] Kong Xiangbing,Shu Ning,Tao Jianbin,et al.ANew Spectral Similarity Measure Based on MultipleFeatures Intergration[J].Spectroscopy and Spec-tral Analysis,2011,31(8):2 166-2 170(孔祥兵,舒宁,陶建斌,等.一种基于多特征融合的新型光谱相似性测度[J].光谱学与光谱分析,2011,31(8):2 166-2 170)[4] Hosseini R S,Homayouni S,Safari R.ModifiedAlgorithm Based on Support Vector Machines forCclassification of Hyperspectral Images in a Similar-ity Space[J].Journal of Applied Remote Sensing,2012(6):3 115-3 123[5] Wu C,Chang C.Soft Decision-Made HyperspectralMeasures for Target Discrimination and Classfica-tion[J].Proc Soc Photo Opt Instrum Eng,2009(1):7 457[6] Chang C C,Lin C J.LIBSVM:A Library for Sup-port Vector Machines,2012[EB/OL].http://www.csie.ntu.edu.tw/~cjlin/libsvm/,2012[7] Shen Zhaoqing,Shu Ning,Tao Jianbin.An Algo-rithm of Weightd“1Vm”SVM Multi-classificationfor Hyperspectral Remote Sensing Image with NPA [J].Geomatics and Information Science of WuhanUniversity,2009,34(12):1 444-1 447(沈照庆,舒宁,陶建斌.一种基于NPA的加权1VmSVM高光谱影像分类算法[J].武汉大学学报·信息科学版,2009,34(12):1 444-1 447)[8] Tan Kun,Du Peijun,Wang Xiaomei.Multi-ClassSupport Vector Machine Classifier Based on Separa-bility Measure for Hyperspectral Remote SensingImage Classification[J].Geomatics and Informa-tion Science of Wuhan University,2011,36(2):171-175(谭琨,杜培军,王小美.利用分离性测度多类支持向量机进行高光谱遥感影像分类[J].武汉大学学报·信息科学版,2011,36(2):171-175)[9] Shen Zhaoqing,Shu Ning,Tao Jianbin.On SVMClassification Algorithm of Hyperspectral RS Im-agery Without Penalty Coefficient[J].Bulletin ofSurveying and Mapping,2009(6):22-25(沈照庆,舒宁,陶建斌.无惩罚系数SVM高光谱影像分类算法研究[J].测绘通报,2009(6):22-25)616武汉大学学报·信息科学版2015年5月

Catalog

    Article views (1253) PDF downloads (620) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return