融合空谱特征和集成超限学习机的高光谱图像分类
|
摘要
为提高高光谱图像的分类精度,提出了一种融合空谱特征和集成超限学习机的高光谱图像分类方法。首先结合每个像素邻域的光谱信息提取空谱特征向量;考虑到高光谱相邻波段信息具有一定的相关性,先对提取的特征向量进行平均分组,然后从每个区间随机选择若干个波段进行组合,采用具有快速学习能力的超限学习机训练分类器。为提高分类模型的泛化能力,基于集成学习思想,对提取的空谱特征进行多次抽样,训练得到多个弱分类器,最后采用投票表决法得到用于高光谱图像分类的强分类器。采用3个典型高光谱数据进行了分类试验,试验结果表明,提出的算法总体分类精度较优,尤其当训练样本数较少时能取得较高的分类精度。提出的算法具有可调参数少、训练速度快、分类精度高等优点,具有广阔的应用前景。
To improve hyperspectral image classification accuracy,a classification method based on combination of spatial-spectral features and ensemble extreme learning machines is proposed in this paper.First,a spatialspectral feature vector for each pixel is extracted using its neighboring information.Considering the strong correlation relationship between neighboring bands in a hyperspectral image,average grouping is performed for the extracted features,and a certain number of bands are first selected randomly from each interval and then combined to form a new feature with fewer dimensions.Extreme learning machine which can be trained fast is used to train a classifier.To improve the generalization performance of the learned model,several rounds of sampling are carried out based on ensemble learning theory,and several weak classifiers are trained and then combined to build a strong classifier using majority vote method.The classification experiments are performed using three typical hyperspectral image datasets,and the experimental results demonstrate that,the proposed algorithm can achieve preferable results compared with the state-of-the-art classifiers.It can achieve better classification accuracies when fewer training samples are used.The proposed algorithm has the advantages of few adjustable parameters,fast training speed,and high classification accuracy,and can be applied in many areas.
To improve hyperspectral image classification accuracy,a classification method based on combination of spatial-spectral features and ensemble extreme learning machines is proposed in this paper.First,a spatialspectral feature vector for each pixel is extracted using its neighboring information.Considering the strong correlation relationship between neighboring bands in a hyperspectral image,average grouping is performed for the extracted features,and a certain number of bands are first selected randomly from each interval and then combined to form a new feature with fewer dimensions.Extreme learning machine which can be trained fast is used to train a classifier.To improve the generalization performance of the learned model,several rounds of sampling are carried out based on ensemble learning theory,and several weak classifiers are trained and then combined to build a strong classifier using majority vote method.The classification experiments are performed using three typical hyperspectral image datasets,and the experimental results demonstrate that,the proposed algorithm can achieve preferable results compared with the state-of-the-art classifiers.It can achieve better classification accuracies when fewer training samples are used.The proposed algorithm has the advantages of few adjustable parameters,fast training speed,and high classification accuracy,and can be applied in many areas.
引文
[1]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.TONG Qingxi,ZHANG Bing,ZHENG Lanfen.Hyperspectral Remote Sensing[M].Beijing:Higher Education Press,2006.
[2]PU Hanye,CHEN Zhao,WANG Bin,et al.A Novel Spatial-spectral Similarity Measure for Dimensionality Reduction and Classification of Hyperspectral Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(11):7008-7022.
[3]孙伟伟.基于流形学习的高光谱影像降维理论与方法研究[J].测绘学报,2014,43(4):439.DOI:10.13485/j.cnki.11-2089.2014.0066.SUN Weiwei.Theory and Methods of Dimensionality Reduction Using Manifold Learning for Hyperspectral Imagery[J].Acta Geodaetica et Cartographica Sinica,2014,43(4):439.DOI:10.13485/j.cnki.11-2089.2014.0066.
[4]GUO B,GUNN S R,DAMPER R I,et al.Band Selection for Hyperspectral Image Classification Using Mutual Information[J].IEEE Geoscience and Remote Sensing Letters,2006,3(4):522-526.
[5]SU Hongjun,YONG Bin,DU Qian.Hyperspectral Band Selection Using Improved Firefly Algorithm[J].IEEE Geoscience and Remote Sensing Letters,2016,13(1):68-72.
[6]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.FAN Liheng,LJunwei,DENG Jiangsheng.Classification of Hyperspectral Remote Sensing Images Based on Bands Grouping and Classification Ensembles[J].Acta Optica Sinica,2014,34(9):0910002.
[7]丁胜,袁修孝,陈黎.粒子群优化算法用于高光谱遥感影像分类的自动波段选择[J].测绘学报,2010,39(3):257-263.DING Sheng,YUAN Xiuxiao,CHEN Li.Automatic Band Selection of Hyperspectral Remote Sensing Image Classification Using Particle Swarm Optimization[J].Acta Geodaetica et Cartographica Sinica,2010,39(3):257-263.
[8]张帆,杜博,张良培,等.一种结合波段分组特征和形态学特征的高光谱图像分类方法[J].计算机科学,2014,41(12):275-279.ZHANG Fan,DU Bo,ZHANG Liangpei,et al.Band Grouping Based Hyperspectral Image Classification Using Mathematical Morphology and Support Vector Machines[J].Computer Science,2014,41(12):275-279.
[9]谭熊,余旭初,秦进春,等.高光谱影像的多核SVM分类[J].仪器仪表学报,2014,35(2):405-411.TAN Xiong,YU Xuchu,QIN Jinchun,et al.Multiple Kernel SVM Classification for Hyperspectral Images[J].Chinese Journal of Scientific Instrument,2014,35(2):405-411.
[10]GAN Le,XIA Junshi,DU Peijun,et al.Class-oriented Weighted Kernel Sparse Representation With Region-level Kernel for Hyperspectral Imagery Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2018,11(4):1118-1130.
[11]杨钊霞,邹峥嵘,陶超,等.空-谱信息与稀疏表示相结合的高光谱遥感影像分类[J].测绘学报,2015,44(7):775-781.DOI:10.11947/j.AGCS.2015.20140207.YANG Zhaoxia,ZOU Zhengrong,TAO Chao,et al.Hyperspectral Image Classification Based on the Combination of Spatial-spectral Feature and Sparse Representation[J].Acta Geodaetica et Cartographica Sinica,2015,44(7):775-781.DOI:10.11947/j.AGCS.2015.20140207.
[12]TOKSZ M A,ULUSOY6)I.Hyperspectral Image Classification via Basic Thresholding Classifier[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(7):4039-4051.
[13]LI Wei,DU Qian,ZHANG Fan,et al.CollaborativeRepresentation-based Nearest Neighbor Classifier for Hyperspectral Imagery[J].IEEE Geoscience and Remote Sensing Letters,2015,12(2):389-393.
[14]BO Chunjuan,LU Huchuan,WANG Dong.Hyperspectral Image Classification via JCR and SVM Models with Decision Fusion[J].IEEE Geoscience and Remote Sensing Letters,2016,13(2):177-181.
[15]SAMAT A,DU Peijun,LIU Sicong,et al.E2LMs:Ensemble Extreme Learning Machines for Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(4):1060-1069.
[16]LI Wei,WU Guodong,ZHANG Fan,et al.Hyperspectral Image Classification Using Deep Pixel-pair Features[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(2):844-853.
[17]HUANG Gao,HUANG Guangbin,SONG Shiji,et al.Trends in Extreme Learning Machines:A Review[J].Neural Networks,2015,61:32-48.
[18]LI Jiaojiao,DU Qian,LI Wei,et al.Optimizing Extreme Learning Machine for Hyperspectral Image Classification[J].Journal of Applied Remote Sensing,2015,9(1):097296.
[19]ZHOU Yicong,PENG Jiangtao,CHEN C L P.Extreme Learning Machine With Composite Kernels for Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(6):2351-2360.
[20]张春霞,张讲社.选择性集成学习算法综述[J].计算机学报,2011,34(8):1399-1410.ZHANG Chunxia,ZHANG Jiangshe.A Survey of Selective Ensemble Learning Algorithms[J].Chinese Journal of Computers,2011,34(8):1399-1410.
[21]BREIMAN L.Bagging Predictors[J].Machine Learning,1996,24(2):123-140.
[22]BREIMAN L.Random Forests[J].Machine Learning,2001,45(1):5-32.
[23]张春森,郑艺惟,黄小兵,等.高光谱影像光谱-空间多特征加权概率融合分类[J].测绘学报,2015,44(8):909-918.DOI:10.11947/j.AGCS.2015.20140544.ZHANG Chunsen,ZHENG Yiwei,HUANG Xiaobing,et al.Hyperspectral Image Classification Based on the Weighted Probabilistic Fusion of Multiple Spectral-spatial Features[J].Acta Geodaetica et Cartographica Sinica,2015,44(8):909-918.DOI:10.11947/j.AGCS.2015.20140544.
[24]MAIRAL J,BACH F,PONCE J,et al.Online Learning for Matrix Factorization and Sparse Coding[J].Journal of Machine Learning Research,2010,11:19-60.
[25]MAIRAL J,BACH F,PONCE J.Sparse Modeling for Image and Vision Processing[J].Foundations and Trends in Computer Graphics and Vision,2014,8(2-3):85-283.
[26]ZHANG Erlei,JIAO Licheng,ZHANG Xiangrong,et al.Class-level Joint Sparse Representation for Multifeaturebased Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(9):4160-4177.
[27]FANG Leyuan,WANG Cheng,LI Shutao,et al.Hyperspectral Image Classification via Multiple-feature-based Adaptive Sparse Representation[J].IEEE Transactions on Instrumentation and Measurement,2017,66(7):1646-1657.
[2]PU Hanye,CHEN Zhao,WANG Bin,et al.A Novel Spatial-spectral Similarity Measure for Dimensionality Reduction and Classification of Hyperspectral Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(11):7008-7022.
[3]孙伟伟.基于流形学习的高光谱影像降维理论与方法研究[J].测绘学报,2014,43(4):439.DOI:10.13485/j.cnki.11-2089.2014.0066.SUN Weiwei.Theory and Methods of Dimensionality Reduction Using Manifold Learning for Hyperspectral Imagery[J].Acta Geodaetica et Cartographica Sinica,2014,43(4):439.DOI:10.13485/j.cnki.11-2089.2014.0066.
[4]GUO B,GUNN S R,DAMPER R I,et al.Band Selection for Hyperspectral Image Classification Using Mutual Information[J].IEEE Geoscience and Remote Sensing Letters,2006,3(4):522-526.
[5]SU Hongjun,YONG Bin,DU Qian.Hyperspectral Band Selection Using Improved Firefly Algorithm[J].IEEE Geoscience and Remote Sensing Letters,2016,13(1):68-72.
[6]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.FAN Liheng,LJunwei,DENG Jiangsheng.Classification of Hyperspectral Remote Sensing Images Based on Bands Grouping and Classification Ensembles[J].Acta Optica Sinica,2014,34(9):0910002.
[7]丁胜,袁修孝,陈黎.粒子群优化算法用于高光谱遥感影像分类的自动波段选择[J].测绘学报,2010,39(3):257-263.DING Sheng,YUAN Xiuxiao,CHEN Li.Automatic Band Selection of Hyperspectral Remote Sensing Image Classification Using Particle Swarm Optimization[J].Acta Geodaetica et Cartographica Sinica,2010,39(3):257-263.
[8]张帆,杜博,张良培,等.一种结合波段分组特征和形态学特征的高光谱图像分类方法[J].计算机科学,2014,41(12):275-279.ZHANG Fan,DU Bo,ZHANG Liangpei,et al.Band Grouping Based Hyperspectral Image Classification Using Mathematical Morphology and Support Vector Machines[J].Computer Science,2014,41(12):275-279.
[9]谭熊,余旭初,秦进春,等.高光谱影像的多核SVM分类[J].仪器仪表学报,2014,35(2):405-411.TAN Xiong,YU Xuchu,QIN Jinchun,et al.Multiple Kernel SVM Classification for Hyperspectral Images[J].Chinese Journal of Scientific Instrument,2014,35(2):405-411.
[10]GAN Le,XIA Junshi,DU Peijun,et al.Class-oriented Weighted Kernel Sparse Representation With Region-level Kernel for Hyperspectral Imagery Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2018,11(4):1118-1130.
[11]杨钊霞,邹峥嵘,陶超,等.空-谱信息与稀疏表示相结合的高光谱遥感影像分类[J].测绘学报,2015,44(7):775-781.DOI:10.11947/j.AGCS.2015.20140207.YANG Zhaoxia,ZOU Zhengrong,TAO Chao,et al.Hyperspectral Image Classification Based on the Combination of Spatial-spectral Feature and Sparse Representation[J].Acta Geodaetica et Cartographica Sinica,2015,44(7):775-781.DOI:10.11947/j.AGCS.2015.20140207.
[12]TOKSZ M A,ULUSOY6)I.Hyperspectral Image Classification via Basic Thresholding Classifier[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(7):4039-4051.
[13]LI Wei,DU Qian,ZHANG Fan,et al.CollaborativeRepresentation-based Nearest Neighbor Classifier for Hyperspectral Imagery[J].IEEE Geoscience and Remote Sensing Letters,2015,12(2):389-393.
[14]BO Chunjuan,LU Huchuan,WANG Dong.Hyperspectral Image Classification via JCR and SVM Models with Decision Fusion[J].IEEE Geoscience and Remote Sensing Letters,2016,13(2):177-181.
[15]SAMAT A,DU Peijun,LIU Sicong,et al.E2LMs:Ensemble Extreme Learning Machines for Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(4):1060-1069.
[16]LI Wei,WU Guodong,ZHANG Fan,et al.Hyperspectral Image Classification Using Deep Pixel-pair Features[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(2):844-853.
[17]HUANG Gao,HUANG Guangbin,SONG Shiji,et al.Trends in Extreme Learning Machines:A Review[J].Neural Networks,2015,61:32-48.
[18]LI Jiaojiao,DU Qian,LI Wei,et al.Optimizing Extreme Learning Machine for Hyperspectral Image Classification[J].Journal of Applied Remote Sensing,2015,9(1):097296.
[19]ZHOU Yicong,PENG Jiangtao,CHEN C L P.Extreme Learning Machine With Composite Kernels for Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(6):2351-2360.
[20]张春霞,张讲社.选择性集成学习算法综述[J].计算机学报,2011,34(8):1399-1410.ZHANG Chunxia,ZHANG Jiangshe.A Survey of Selective Ensemble Learning Algorithms[J].Chinese Journal of Computers,2011,34(8):1399-1410.
[21]BREIMAN L.Bagging Predictors[J].Machine Learning,1996,24(2):123-140.
[22]BREIMAN L.Random Forests[J].Machine Learning,2001,45(1):5-32.
[23]张春森,郑艺惟,黄小兵,等.高光谱影像光谱-空间多特征加权概率融合分类[J].测绘学报,2015,44(8):909-918.DOI:10.11947/j.AGCS.2015.20140544.ZHANG Chunsen,ZHENG Yiwei,HUANG Xiaobing,et al.Hyperspectral Image Classification Based on the Weighted Probabilistic Fusion of Multiple Spectral-spatial Features[J].Acta Geodaetica et Cartographica Sinica,2015,44(8):909-918.DOI:10.11947/j.AGCS.2015.20140544.
[24]MAIRAL J,BACH F,PONCE J,et al.Online Learning for Matrix Factorization and Sparse Coding[J].Journal of Machine Learning Research,2010,11:19-60.
[25]MAIRAL J,BACH F,PONCE J.Sparse Modeling for Image and Vision Processing[J].Foundations and Trends in Computer Graphics and Vision,2014,8(2-3):85-283.
[26]ZHANG Erlei,JIAO Licheng,ZHANG Xiangrong,et al.Class-level Joint Sparse Representation for Multifeaturebased Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(9):4160-4177.
[27]FANG Leyuan,WANG Cheng,LI Shutao,et al.Hyperspectral Image Classification via Multiple-feature-based Adaptive Sparse Representation[J].IEEE Transactions on Instrumentation and Measurement,2017,66(7):1646-1657.