利用信息熵的高光谱遥感影像降维方法
|
摘要
高光谱遥感影像以其众多的波段数目,为地表观测提供近乎连续的波谱数据;然而海量的高光谱遥感影像存在着大量的信息冗余,为数据的处理带来了挑战。因此在对高光谱遥感影像进行存储、分析及可视化等操作之前,对高光谱遥感影像降维处理成为预处理的关键环节之一。利用信息熵理论,将高光谱遥感影像的各波段抽象为具有相关性的独立个体,设计了高光谱遥感影像的决策表矩阵,进而计算各波段的信息熵,量化各波段的信息量,从而将各波段根据信息增益进行排序。用户可根据高光谱遥感影像应用的精度需求,按排序选择波段组合,从而达到降维目的。以遥感分类结果的精度评价为例,对高光谱遥感降维方法的可行性和优越性进行评价。实验结果表明,该方法相较其他特征选取降维方法,能获得更高的分类精度。
Hyperspectral remote sensing images provide almost continuous spectrum for the surface observation of the earth. However, there are more redundancy information within the bands, which pose challenges to storage, analysis and visualization of the hyperspectral remote sensing images. Thus, dimensionality reduction for hyperspectral remote sensing images become a key step of preprocessing. In this paper, the theory of information entropy is adopted to design the dimensionality reduction method. Each band of hyperspectral remote sensing images are abstracted as independent individual, and the decision table matrix of hyperspectral remote sensing images are designed, and then the bands are ordered based on the information gain. According to the accuracy requirement of the analysis of hyperspectral remote sensing images, the different bands are selected based on the ordered bands, which are considered as the results of the dimensionality reduction. Taking the classification accuracy of remote sensing as an example to evaluate the feasibility and superiority of the dimensionality reduction methods in hyperspectral remote sensing, and based on the experimental results, the proposed method has marked advantages and outperformed other methods.
Hyperspectral remote sensing images provide almost continuous spectrum for the surface observation of the earth. However, there are more redundancy information within the bands, which pose challenges to storage, analysis and visualization of the hyperspectral remote sensing images. Thus, dimensionality reduction for hyperspectral remote sensing images become a key step of preprocessing. In this paper, the theory of information entropy is adopted to design the dimensionality reduction method. Each band of hyperspectral remote sensing images are abstracted as independent individual, and the decision table matrix of hyperspectral remote sensing images are designed, and then the bands are ordered based on the information gain. According to the accuracy requirement of the analysis of hyperspectral remote sensing images, the different bands are selected based on the ordered bands, which are considered as the results of the dimensionality reduction. Taking the classification accuracy of remote sensing as an example to evaluate the feasibility and superiority of the dimensionality reduction methods in hyperspectral remote sensing, and based on the experimental results, the proposed method has marked advantages and outperformed other methods.
引文
[1]杜培军,夏俊士,薛朝辉,等.高光谱遥感影像分类研究进展[J].遥感学报,2016,20(2):236-256.
[2]Khoder M,Kashana S,Khoder J,et al.Multicriteria classification method for dimensionality reduction adapted to hyperspectral images[J].Journal of Applied Remote Sensing,2017,11(2):025001.
[3]Laparra V,Malo J,Camps-Valls G.Dimensionality reduction via regression in hyperspectral imagery[J].IEEE Journal of Selected Topics in Signal Processing,2015,9(6):1026-1036.
[4]Carreira-Perpinán M A.A review of dimension reduction techniques[D].University of Sheffield.Department of Computer Science,1997.
[5]Guyon I,Elisseeff A.An introduction to feature extraction[C]//NIPS Workshop on Feature Extracion,2003:1-25.
[6]Hsu P H.Feature extraction of hyperspectral images using wavelet and matching pursuit[J].ISPRS Journal of Photogrammetry and Remote Sensing,2007,62(2):78-92.
[7]Pal M,Foody G M.Feature selection for classification of hyperspectral data by SVM[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(5):2297-2307.
[8]谭雨蕾.基于特征度量的高光谱遥感影像波段选择方法研究[D].长春:吉林大学,2017.
[9]李垒,任越美.基于随机森林的高光谱遥感图像分类[J].计算机工程与应用,2016,52(24):189-193.
[10]程圆娥,周绍光,袁春琦,等.基于主动深度学习的高光谱影像分类[J].计算机工程与应用,2017,53(17):192-196.
[11]赵鹏飞,周绍光,裔阳,等.基于SLIC和主动学习的高光谱遥感图像分类方法[J].计算机工程与应用,2017,53(3):183-187.
[12]Bellman R E.Adaptive control processes:a guided tour[M].[S.l.]:Princeton University Press,2015.
[13]Lei T C,Wan S,Chou T Y.The comparison of PCA and discrete rough set for feature extraction of remote sensing image classification:a case study on rice classification,Taiwan[J].Computational Geosciences,2008,12(1):1-14.
[14]孙墨寒.高光谱数据误差估计及降维方法研究[D].北京:中国地质大学,2013.
[15]Shchurenkova E.Dimension reduction using independent component analysis with an application in business psychology[D].University of British Columbia,2017.
[16]Imani M,Ghassemian H.Feature reduction of hyperspectral images:discriminant analysis and the first principal component[J].Journal of AI and Data Mining,2015,3(1):1-9.
[17]魏芳洁.高光谱图像波段选择方法的研究[D].哈尔滨:哈尔滨工程大学,2013.
[18]张爱武,杜楠,康孝岩,等.非线性变换和信息相邻相关的高光谱自适应波段选择[J].红外与激光工程,2017,46(5):221-229.
[19]余晓敏,湛飞并,廖明生,等.利用改进SEaTH算法的面向对象分类特征选择方法[J].武汉大学学报(信息科学版),2012,37(8):921-924.
[20]Kumar V,Rao V N.Parallel depth first search.Part II.analysis[J].International Journal of Parallel Programming,1987,16(6):501-519.
[21]李明星.多粒度粗糙集的理论研究及其应用[D].江苏镇江:江苏科技大学,2014.
[22]董哲.基于关系信息熵的特征选择[D].辽宁锦州:渤海大学,2016.
[23]刘盾.基于粗糙集理论的多属性决策方法[D].成都:西南交通大学,2011.
[24]杨诸胜.高光谱图像降维及分割研究[D].西安:西北工业大学,2006.
[25]冯燕,何明一,宋江红,等.基于独立成分分析的高光谱图像数据降维及压缩[J].电子与信息学报,2007(12):2871-2875.
[26]夏欢欢.基于形态学滤波的最小噪声分离及其应用[D].成都:成都理工大学,2013.
[27]Marill T,Green D.On the effectiveness of receptors in recognition systems[J].IEEE Transactions on Information Theory,1963,9(1):11-17.
[28]蒋玉娇,王晓丹,王文军,等.一种基于PCA和ReliefF的特征选择方法[J].计算机工程与应用,2010,46(26):170-172.
[2]Khoder M,Kashana S,Khoder J,et al.Multicriteria classification method for dimensionality reduction adapted to hyperspectral images[J].Journal of Applied Remote Sensing,2017,11(2):025001.
[3]Laparra V,Malo J,Camps-Valls G.Dimensionality reduction via regression in hyperspectral imagery[J].IEEE Journal of Selected Topics in Signal Processing,2015,9(6):1026-1036.
[4]Carreira-Perpinán M A.A review of dimension reduction techniques[D].University of Sheffield.Department of Computer Science,1997.
[5]Guyon I,Elisseeff A.An introduction to feature extraction[C]//NIPS Workshop on Feature Extracion,2003:1-25.
[6]Hsu P H.Feature extraction of hyperspectral images using wavelet and matching pursuit[J].ISPRS Journal of Photogrammetry and Remote Sensing,2007,62(2):78-92.
[7]Pal M,Foody G M.Feature selection for classification of hyperspectral data by SVM[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(5):2297-2307.
[8]谭雨蕾.基于特征度量的高光谱遥感影像波段选择方法研究[D].长春:吉林大学,2017.
[9]李垒,任越美.基于随机森林的高光谱遥感图像分类[J].计算机工程与应用,2016,52(24):189-193.
[10]程圆娥,周绍光,袁春琦,等.基于主动深度学习的高光谱影像分类[J].计算机工程与应用,2017,53(17):192-196.
[11]赵鹏飞,周绍光,裔阳,等.基于SLIC和主动学习的高光谱遥感图像分类方法[J].计算机工程与应用,2017,53(3):183-187.
[12]Bellman R E.Adaptive control processes:a guided tour[M].[S.l.]:Princeton University Press,2015.
[13]Lei T C,Wan S,Chou T Y.The comparison of PCA and discrete rough set for feature extraction of remote sensing image classification:a case study on rice classification,Taiwan[J].Computational Geosciences,2008,12(1):1-14.
[14]孙墨寒.高光谱数据误差估计及降维方法研究[D].北京:中国地质大学,2013.
[15]Shchurenkova E.Dimension reduction using independent component analysis with an application in business psychology[D].University of British Columbia,2017.
[16]Imani M,Ghassemian H.Feature reduction of hyperspectral images:discriminant analysis and the first principal component[J].Journal of AI and Data Mining,2015,3(1):1-9.
[17]魏芳洁.高光谱图像波段选择方法的研究[D].哈尔滨:哈尔滨工程大学,2013.
[18]张爱武,杜楠,康孝岩,等.非线性变换和信息相邻相关的高光谱自适应波段选择[J].红外与激光工程,2017,46(5):221-229.
[19]余晓敏,湛飞并,廖明生,等.利用改进SEaTH算法的面向对象分类特征选择方法[J].武汉大学学报(信息科学版),2012,37(8):921-924.
[20]Kumar V,Rao V N.Parallel depth first search.Part II.analysis[J].International Journal of Parallel Programming,1987,16(6):501-519.
[21]李明星.多粒度粗糙集的理论研究及其应用[D].江苏镇江:江苏科技大学,2014.
[22]董哲.基于关系信息熵的特征选择[D].辽宁锦州:渤海大学,2016.
[23]刘盾.基于粗糙集理论的多属性决策方法[D].成都:西南交通大学,2011.
[24]杨诸胜.高光谱图像降维及分割研究[D].西安:西北工业大学,2006.
[25]冯燕,何明一,宋江红,等.基于独立成分分析的高光谱图像数据降维及压缩[J].电子与信息学报,2007(12):2871-2875.
[26]夏欢欢.基于形态学滤波的最小噪声分离及其应用[D].成都:成都理工大学,2013.
[27]Marill T,Green D.On the effectiveness of receptors in recognition systems[J].IEEE Transactions on Information Theory,1963,9(1):11-17.
[28]蒋玉娇,王晓丹,王文军,等.一种基于PCA和ReliefF的特征选择方法[J].计算机工程与应用,2010,46(26):170-172.