面向高光谱影像分类的多特征流形鉴别嵌入
|
摘要
鉴于传统维数约减方法对高光谱遥感影像进行降维时,往往只利用了单一的光谱特征,限制了分类性能的提升。提出一种基于多特征流形鉴别嵌入的维数约减方法,该方法首先提取高光谱数据的LBP(Local Binary Patterns)纹理特征,然后利用样本点的光谱-LBP特征联合距离及类别信息构建类内图和类间图以发现高光谱影像中的鉴别流形结构,在低维嵌入空间中不仅保持来自同一像素的光谱和纹理特征的相似性,而且使同类点尽可能紧致、不同类点远离,实现空-谱联合低维鉴别特征提取,以有效提高地物分类性能。在Indian Pines和黑河高光谱遥感数据集上的实验表明,本文算法的分类精度在不同实验条件下均优于传统的维数约减方法,其分类精度可达95.05%和96.20%,在较少训练样本条件下优势更为明显,有利于实际应用。
The traditional Dimensionality Reduction(DR)methods consider the spectral features but ignores useful spatial information in HSI.To overcome this problem,this paper proposed a new dimensionality reduction method called Multi-Feature Manifold Discriminant Embedding(MFDE).First,the MFDE method extracted the features of the local binary pattern from HSI data.Next,the with-class and between-class graphs were constructed using sample labels to exploit the local manifold structure.Then,an optimal object function was designed to learn the combined spatial-spectral features by compacting the intra-class samples and simultaneously separating the inter-class samples.Thus,the discriminative ability of embedding features was improved.Experimental results in the Indian Pines and Heihe hyperspectral data sets show that the proposed MFDE method performs better than some state-of-the-art DR methods in most cases and achieves an overall classification accuracy of95.05%and 96.20%,respectively.Its advantage is more significant for less training samples,making it more conducive to practical applications.
The traditional Dimensionality Reduction(DR)methods consider the spectral features but ignores useful spatial information in HSI.To overcome this problem,this paper proposed a new dimensionality reduction method called Multi-Feature Manifold Discriminant Embedding(MFDE).First,the MFDE method extracted the features of the local binary pattern from HSI data.Next,the with-class and between-class graphs were constructed using sample labels to exploit the local manifold structure.Then,an optimal object function was designed to learn the combined spatial-spectral features by compacting the intra-class samples and simultaneously separating the inter-class samples.Thus,the discriminative ability of embedding features was improved.Experimental results in the Indian Pines and Heihe hyperspectral data sets show that the proposed MFDE method performs better than some state-of-the-art DR methods in most cases and achieves an overall classification accuracy of95.05%and 96.20%,respectively.Its advantage is more significant for less training samples,making it more conducive to practical applications.
引文
[1]黄鸿,陈美利,段宇乐,等.空-谱协同流形重构误差的高光谱影像分类[J].光学精密工程,2018,26(7):1827-1836.HUANG H,CHENG M L,DUAN Y L,et al..Hyperspectral image classification with combination of spatial-spectral and manifold reconstruction[J].Opt.Precision Eng.,2018,26(7):1827-1836.(in Chinese)
[2]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.DU P J,XIA J SH,XUE ZH H,et al..Progress of hyperspectral remote sensing image classification[J].Journal of remote sensing,2016,20(2):236-256.(in Chinese)
[3]LUO F L,DU B,ZHANG L P,et al..Feature learning using spatial-spectral hypergraph discriminant analysis for hyperspectral image[J].IEEETransactions on Cybernetics,2018,PP(99):1-14.
[4]何芳,王榕,于强,等.加权空谱局部保持投影的高光谱图像特征提取[J].光学精密工程,2017,25(1):263-273.HE F,WANG R,YU Q,et al..Feature extraction of hyperspectral images of weighted spatial and spectral locality preserving projection[J].Opt.Precision Eng.,2017,25(1):263-273.(in Chinese)
[5]FENG F,LI W,DU Q,et al..Dimensionality reduction of hyperspectral image with graph-based discriminant analysis considering spectral similarity[J].Remote Sensing,2017,9(4):323.
[6]FANG L,WANG C,LI S,et al..Hyperspectral image classification via multiple-feature-based adaptive sparse representation[J].IEEE Transactions on Instrumentation&Measurement,2017,66(7):1646-1657.
[7]XU Y H,ZHANG L P,DU B,et al..Spectralspatial unified networks for hyperspectral image classification[J].IEEE Transactions on Geoscience&Remote Sensing,2018,PP(99):1-17.
[8]HUANG H,DUAN Y L,SHI G Y,et al..Fusion of weighted mean reconstruction and SVMCK for hyperspectral image classification[J].IEEE Access,2018,6(99):15224-15235.
[9]王庆超,付光远,汪洪桥,等.多核融合多尺度特征的高光谱影像地物分类[J].光学精密工程,2018,26(4):980-988.WANG Q CH,FU G Y,WANG H Q,et al..Fusion of multi-scale feature using multiple kernel learning for hyperspectral image land cover classification[J].Opt.Precision Eng.,2018,26(4):980-988.(in Chinese)
[10]JIANG J J,HU R M,WANG Z Y,et al..CDM-MA:Coupled discriminant multi-manifold analysis for matching low-resolution face images[J].Signal Processing,2016,124:162-172.
[11]BONIFAZI G,CAPOBIANCO G,SERRANTI S.Asbestos containing materials detection and classification by the use of hyperspectral imaging[J].Journal of Hazardous Materials,2018,344:981-993.
[12]LUO R B,LIAO W Z,PHILIPS W,et al..An improved semi-supervised local discriminant analysis for feature extraction of hyperspectral image[J].IEEE Transactions on Geoscience&Remote Sensing,2015,51(1):184-198.
[13]李志敏,张杰,黄鸿,等.面向高光谱图像分类的半监督丛流形学习[J].光学精密工程,2015,23(5):1434-1442.LI ZH M,ZHANG J,HUANG H,et al..Semisupervised bundle manifold learning for hyperspectral image classification[J].Opt.Precision Eng.,2015,23(5):1434-1442.(in Chinese)
[14]LI W,ZHANG L P,ZHANG L F,et al..GPU parallel implementation of isometric mapping for hyperspectral classification[J].IEEE Geoscience&Remote Sensing Letters,2017,14(9):1532-1539.
[15]ZHANG L L,ZHAO C H.Sparsity divergence index based on locally linear embedding for hyperspectral anomaly detection[J].Journal of Applied Remote Sensing,2016,10(2):25-26.
[16]LV M,ZHAO X,LIU L,et al..Discriminant collaborative neighborhood preserving embedding for hyperspectral imagery[J].Journal of Applied Remote Sensing,2017,11(4):1.
[17]DENG Y J,LI H C,PAN L,et al..Modified tensor locality preserving projection for dimensionality reduction of hyperspectral images[J].IEEE Geoscience&Remote Sensing Letters,2018,15(2):277-281.
[18]LU Y,LAI Z,FAN Z,et al..Manifold discriminant regression learning for image classification[J].Neurocomputing,2015,166(C):475-486.
[19]JIA J,RUAN Q,JIN Y.Geometric preserving local fisher discriminant analysis for person re-identification[J].Neurocomputing,2016,205(C):92-105.
[20]LUO F L,HUANG H,DUAN Y L,et al..Local geometric structure feature for dimensionality reduction of hyperspectral imagery[J].Remote Sensing,2017,9(8):790.
[21]LI W,CHEN C,SU H,et al..Local binary patterns and extreme learning machine for hyperspectral imagery classification[J].IEEE Transactions on Geoscience&Remote Sensing,2015,53(7):3681-3693.
[22]MAURO D M,JON A B,BIORN W.Morphological attribute profiles for the analysis of very high resolution images[J].IEEE Transactions on Geoscience&Remote Sensing,2010,48(10):3747-3762.
[23]LI J,HUANG X,GAMBA P,et al..Multiple feature learning for hyperspectral image classification[J].IEEE Transactions on Geoscience&Remote Sensing,2015,53(3):1592-1606.
[24]SONG C Y,YANG F J,LI P J.Rotation invariant texture measured by local binary pattern for remote sensing image classification[C].2010 Second International Workshop on Education Technology and Computer Science,Wuhan,P.R.China,2010,3(3):3-6.
[25]肖青,闻建光.黑河生态水文遥感试验:热红外高光谱航空遥感(2012年7月4日)[Z].黑河计划数据管理中心,2013.doi:10.3972/hiwater.006.2013.db.XIAO Q,WEN J G.HiWATER:Thermal-Infrared Hyperspectral Radiometer(4th,July,2012)[Z].Heihe Plan Science Data Center,2013.doi:10.3972/hiwater.006.2013.db.(in Chinese)
[2]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.DU P J,XIA J SH,XUE ZH H,et al..Progress of hyperspectral remote sensing image classification[J].Journal of remote sensing,2016,20(2):236-256.(in Chinese)
[3]LUO F L,DU B,ZHANG L P,et al..Feature learning using spatial-spectral hypergraph discriminant analysis for hyperspectral image[J].IEEETransactions on Cybernetics,2018,PP(99):1-14.
[4]何芳,王榕,于强,等.加权空谱局部保持投影的高光谱图像特征提取[J].光学精密工程,2017,25(1):263-273.HE F,WANG R,YU Q,et al..Feature extraction of hyperspectral images of weighted spatial and spectral locality preserving projection[J].Opt.Precision Eng.,2017,25(1):263-273.(in Chinese)
[5]FENG F,LI W,DU Q,et al..Dimensionality reduction of hyperspectral image with graph-based discriminant analysis considering spectral similarity[J].Remote Sensing,2017,9(4):323.
[6]FANG L,WANG C,LI S,et al..Hyperspectral image classification via multiple-feature-based adaptive sparse representation[J].IEEE Transactions on Instrumentation&Measurement,2017,66(7):1646-1657.
[7]XU Y H,ZHANG L P,DU B,et al..Spectralspatial unified networks for hyperspectral image classification[J].IEEE Transactions on Geoscience&Remote Sensing,2018,PP(99):1-17.
[8]HUANG H,DUAN Y L,SHI G Y,et al..Fusion of weighted mean reconstruction and SVMCK for hyperspectral image classification[J].IEEE Access,2018,6(99):15224-15235.
[9]王庆超,付光远,汪洪桥,等.多核融合多尺度特征的高光谱影像地物分类[J].光学精密工程,2018,26(4):980-988.WANG Q CH,FU G Y,WANG H Q,et al..Fusion of multi-scale feature using multiple kernel learning for hyperspectral image land cover classification[J].Opt.Precision Eng.,2018,26(4):980-988.(in Chinese)
[10]JIANG J J,HU R M,WANG Z Y,et al..CDM-MA:Coupled discriminant multi-manifold analysis for matching low-resolution face images[J].Signal Processing,2016,124:162-172.
[11]BONIFAZI G,CAPOBIANCO G,SERRANTI S.Asbestos containing materials detection and classification by the use of hyperspectral imaging[J].Journal of Hazardous Materials,2018,344:981-993.
[12]LUO R B,LIAO W Z,PHILIPS W,et al..An improved semi-supervised local discriminant analysis for feature extraction of hyperspectral image[J].IEEE Transactions on Geoscience&Remote Sensing,2015,51(1):184-198.
[13]李志敏,张杰,黄鸿,等.面向高光谱图像分类的半监督丛流形学习[J].光学精密工程,2015,23(5):1434-1442.LI ZH M,ZHANG J,HUANG H,et al..Semisupervised bundle manifold learning for hyperspectral image classification[J].Opt.Precision Eng.,2015,23(5):1434-1442.(in Chinese)
[14]LI W,ZHANG L P,ZHANG L F,et al..GPU parallel implementation of isometric mapping for hyperspectral classification[J].IEEE Geoscience&Remote Sensing Letters,2017,14(9):1532-1539.
[15]ZHANG L L,ZHAO C H.Sparsity divergence index based on locally linear embedding for hyperspectral anomaly detection[J].Journal of Applied Remote Sensing,2016,10(2):25-26.
[16]LV M,ZHAO X,LIU L,et al..Discriminant collaborative neighborhood preserving embedding for hyperspectral imagery[J].Journal of Applied Remote Sensing,2017,11(4):1.
[17]DENG Y J,LI H C,PAN L,et al..Modified tensor locality preserving projection for dimensionality reduction of hyperspectral images[J].IEEE Geoscience&Remote Sensing Letters,2018,15(2):277-281.
[18]LU Y,LAI Z,FAN Z,et al..Manifold discriminant regression learning for image classification[J].Neurocomputing,2015,166(C):475-486.
[19]JIA J,RUAN Q,JIN Y.Geometric preserving local fisher discriminant analysis for person re-identification[J].Neurocomputing,2016,205(C):92-105.
[20]LUO F L,HUANG H,DUAN Y L,et al..Local geometric structure feature for dimensionality reduction of hyperspectral imagery[J].Remote Sensing,2017,9(8):790.
[21]LI W,CHEN C,SU H,et al..Local binary patterns and extreme learning machine for hyperspectral imagery classification[J].IEEE Transactions on Geoscience&Remote Sensing,2015,53(7):3681-3693.
[22]MAURO D M,JON A B,BIORN W.Morphological attribute profiles for the analysis of very high resolution images[J].IEEE Transactions on Geoscience&Remote Sensing,2010,48(10):3747-3762.
[23]LI J,HUANG X,GAMBA P,et al..Multiple feature learning for hyperspectral image classification[J].IEEE Transactions on Geoscience&Remote Sensing,2015,53(3):1592-1606.
[24]SONG C Y,YANG F J,LI P J.Rotation invariant texture measured by local binary pattern for remote sensing image classification[C].2010 Second International Workshop on Education Technology and Computer Science,Wuhan,P.R.China,2010,3(3):3-6.
[25]肖青,闻建光.黑河生态水文遥感试验:热红外高光谱航空遥感(2012年7月4日)[Z].黑河计划数据管理中心,2013.doi:10.3972/hiwater.006.2013.db.XIAO Q,WEN J G.HiWATER:Thermal-Infrared Hyperspectral Radiometer(4th,July,2012)[Z].Heihe Plan Science Data Center,2013.doi:10.3972/hiwater.006.2013.db.(in Chinese)
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |