小波核局部Fisher判别分析的高光谱遥感影像特征提取

doi:10.16451/j.cnki.issn1003-6059.201907006

摘要
图/表
参考文献(0)
相关文章 (15)

全文: PDF (1515 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

为了提高高光谱遥感影像的分类精度,充分利用影像的光谱和局部信息,文中提出小波核局部Fisher判别分析的高光谱遥感影像特征提取方法.通过小波核函数将数据集从低维原始空间映射至高维特征空间,考虑到数据的局部信息,利用加权矩阵计算散度矩阵,对局部Fisher判别准则函数求解最优特征矩阵,使不同类别的样本在高维特征空间中的可分离性更佳.在2个公开高光谱数据集上的实验表明,文中方法的总体分类精度和Kappa系数都有所提高.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张辉
	刘万军
	吕欢欢

关键词 ：高光谱影像分类, 小波核函数, 局部Fisher判别分析, 特征提取

Abstract：

To improve classification accuracies of hyperspectral remote sensing images and make full use of local information, a feature extraction method for hyperspectral remote sensing images based on local Fisher discriminant analysis with wavelet kernel is proposed. Wavelet kernel function is introduced to map data from a low dimensional space to a high dimensional feature space, and a weighted matrix is employed to calculate scatter matrices. Local Fisher discriminant criterion function is solved to obtain the optimal feature matrix and a better separation in high-dimensional feature space. Experimental results on two open hyperspectral datasets show that the overall classification accuracy and Kappa coefficient of the proposed method are improved compared with other methods.

Key words： Hyperspectral Image Classification Wavelet Kernel Function Local Fisher Discriminant Analysis Feature Extraction

收稿日期: 2019-03-21

ZTFLH:

TP 751

基金资助:

国家自然科学基金项目(No.41871379,61540056)、辽宁省自然科学基金指导计划项目(No.20180550450)、辽宁省教育厅重点项目(No.LJ2017ZL003)资助

作者简介: 张辉,博士研究生,主要研究方向为高光谱数据处理.E-mail:zhjordan45@126.com. 刘万军,硕士,教授,主要研究方向为数字图像处理.E-mail:liuwanjun@lntu.edu.cn.吕欢欢(通讯作者),博士,副教授,主要研究方向为高光谱数据处理.E-mail:lvhuanhuan@lntu.edu.cn.

引用本文:

张辉,刘万军,吕欢欢. 小波核局部Fisher判别分析的高光谱遥感影像特征提取[J]. 模式识别与人工智能, 2019, 32(7): 624-632. ZHANG Hui, LIU Wanjun, Lü Huanhuan. Feature Extraction for Hyperspectral Remote Sensing Image Based on Local Fisher Discriminant Analysis with Wavelet Kernel. , 2019, 32(7): 624-632.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201907006 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2019/V32/I7/624

[1] SU H J, ZHAO B, DU Q, et al. Kernel Equation Collaborative Representation with Local Correlation Features for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 2018. DOI: 10.1109/TGRS.2018.2866190.
[2] LI L, SUN C, LIN L L, et al. A Dual-Kernel Spectral-Spatial Cla-ssification Approach for Hyperspectral Images Based on Mahalanobis Distance Metric Learning. Information Sciences, 2018, 429: 260-283.
[3] IMANI M. Manifold Structure Preservative for Hyperspectral Target Detection. Advances in Space Research, 2018, 61(10): 2510-2520.
[4] 杜培军,夏俊士,薛朝辉,等.高光谱遥感影像分类研究进展.遥感学报, 2016, 20(2): 236-256.
(DU P J, XIA J S, XUE Z H, et al. Review of Hyperspectral Remote Sensing Image Classification. Journal of Remote Sensing, 2016, 20(2): 236-256.)
[5] CORSON M R, LUCKE R L, DAVIS C O, et al. The Hyperspectral Imager for the Coastal Ocean (HICO^TM) Environmental Littoral Imaging from the International Space Station // Proc of the IEEE International Geoscience and Remote Sensing Symposium. Washington, USA: IEEE, 2010: 3752-3755.
[6] LI N, HUANG X C, ZHAO H J, et al. Multiparameter Optimization for Mineral Mapping Using Hyperspectral Imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(4): 1348-1357.
[7] 刘艳芳,叶东毅.基于邻域保持学习的无监督特征选择算法.模式识别与人工智能, 2018, 31(12): 1096-1102.
(LIU Y F,YE D Y. Unsupervised Feature Selection Algorithm Based on Neighborhood Preserving Learning. Pattern Recognition and Artificial Intelligence, 2018, 31(12): 1096-1102.)
[8] CHEN G Y, QIAN S E. Denoising of Hyperspectral Imagery Using Principal Component Analysis and Wavelet Shrinkage. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(3): 973-980.
[9] MONCAYO S, DUPONCHEL L, MOUSAVIPAK N, et al. Exploration of Megapixel Hyperspectral LIBS Images Using Principal Component Analysis. Journal of Analytical Atomic Spectrometry, 2018, 33(2): 210-220.
[10] BANDOS T V, BRUZZONE L, CAMPS-VALLS G. Classification of Hyperspectral Images with Regularized Linear Discriminant Analysis. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(3): 862-873.
[11] 蔡竞,王万良,郑建炜,等.基于Fisher判别分析的增量式非负矩阵分解算法.模式识别与人工智能, 2018, 31(6): 505-515.
(CAI J, WAN W L, ZHENG J W, et al. Incremental Non-negative Matrix Factorization Based on Fisher Discriminant Analysis. Pattern Recognition and Artificial Intelligence, 2018, 31(6): 505-515.)
[12] TEIXEIRA A R, TOM A M, LANG E W. Unsupervised Feature Extraction via Kernel Subspace Techniques. Neurocomputing, 2011, 74(5): 820-830.
[13] XIA J S, FALCO N, BENEDIKTSSON J A, et al. Hyperspectral Image Classification with Rotation Random Forest via KPCA. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(4): 1601-1609.
[14] KUO B C, LI C H, YANG J M. Kernel Nonparametric Weighted Feature Extraction for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(4): 1139-1155.
[15] 谭琨,杜培军.基于再生核Hilbert空间的小波核函数支持向量机的高光谱遥感影像分类.测绘学报, 2011, 40(2): 142-147.
(TAN K, DU P J. Wavelet Support Vector Machines Based on Reproducing Kernel Hilbert Space for Hyperspectral Remote Sensing Image Classification. Acta Geodaetica et Cartographica Sinica, 2011, 40(2): 142-147.)
[16] 高明哲,许爱强,张伟.基于自适应核参数优化的小波核相关向量机算法.计算机工程, 2017, 43(9): 245-249.
(GAO M Z, XU A Q, ZHANG W. Wavelet Kernel Relevance Vector Machine Algorithm Based on Adaptive Kernel Parameter Optimization. Computer Engeneering, 2017, 43(9): 245-249.)
[17] ZHANG L, ZHOU W D, JIAO L C. Wavelet Support Vector Machine. IEEE Transactions on Systems, Man and Cybernetics(Cybernetics), 2004, 34(1): 34-39.
[18] 赵春晖,张燚,王玉磊.基于小波核主成分分析的相关向量机高光谱图像分类.电子与信息学报, 2012, 34(8): 1905-1910.
(ZHAO C H, ZHANG Y, WANG Y L. Relevant Vector Machine Classification of Hyperspectral Image Based on Wavelet Kernel Principal Component Analysis. Journal of Electronics and Information Technology, 2012, 34(8): 1905-1910.)
[19] 白文平,刘宗昂,鲁加国.基于小波和独立成分分析的去噪自适应算法.海军航空工程学院学报, 2018, 33(4): 351-355, 388.
(BAI W P, LIU Z A, LU J G. An Adaptive Denoising Algorithm Based on Wavelet Transform and Independent Component Analysis. Journal of Naval Aeronautical and Astronautical University, 2018, 33(4): 351-355, 388.)[20] 白璘,刘盼芝,惠萌.利用小波核最小噪声分离进行高光谱影像SVM分类.武汉大学学报(信息科学版), 2016, 41(5): 624-628, 664.
(BAI L, LIU P Z, HUI M. SVM Classification of Hyperspectral Image Based on Wavelet Kernel Minimum Noise Fraction. Geoma-tics and Information Science of Wuhan University, 2016, 41(5): 624-628, 664.)
[21] 谷雨,徐英,郭宝辉.融合空谱特征和集成超限学习机的高光谱图像分类.测绘学报, 2018, 47(9): 1238-1249.
(GU Y, XU Y, GUO B H. Hyperspectral Image Classification by Combination of Spatial-Spectral Features and Ensemble Extreme Learning Machines. Acta Geodaetica et Cartographica Sinica, 2018, 47(9): 1238-1249.)
[22] 杨国鹏,余旭初,陈伟,等.基于核Fisher判别分析的高光谱遥感影像分类.遥感学报, 2008, 12(4): 579-585.
(YANG G P, YU X C, CHEN W, et al. Hyperspectral Remote Sensing Image Classification Based on Kernel Fisher Discriminant Analysis. Journal of Remote Sensing, 2008, 12(4): 579-585.)
[23] ZELNIK-MANOR L, PERONA P. Self-tuning Spectral Clustering // SAUL L K, WEISS Y, BOTTOU L, eds. Advances in Neural Information Processing Systems 17. Cambridge, USA: The MIT Press, 2005: 1601-1608.
[24] SUGIYAMA M. Dimensionality Reduction of Multimodal Labeled Data by Local Fisher Discriminant Analysis. Journal of Machine Learning Research, 2007, 8(1): 1027-1061.