联合核稀疏多元逻辑回归和TV-L1错误剔除的高光谱图像分类算法

徐金环, 沈煜, 刘鹏飞, 肖亮

电子学报 ›› 2018, Vol. 46 ›› Issue (1) : 175-184.

PDF(17470 KB)
PDF(17470 KB)
电子学报 ›› 2018, Vol. 46 ›› Issue (1) : 175-184. DOI: 10.3969/j.issn.0372-2112.2018.01.024
学术论文

联合核稀疏多元逻辑回归和TV-L1错误剔除的高光谱图像分类算法

  • 徐金环1, 沈煜1, 刘鹏飞2, 肖亮1
作者信息 +

Hyperspectral Image Classification Combining Kernel Sparse Multinomial Logistic Regression and TV-L1 Error Rejection

  • XU Jin-huan1, SHEN Yu1, LIU Peng-fei2, XIAO Liang1
Author information +
文章历史 +

摘要

稀疏多元逻辑回归(SMLR)是高光谱监督分类中的重要方法,然而仅仅利用光谱信息的SMLR忽略了影像本身的空间特征,在少量监督样本下的分类精度和算法的鲁棒性仍明显不足;虽然通过引入核技巧,核稀疏多元逻辑回归(KSMLR)可以部分克服上述缺点,其分类错误仍然有待进一步降低.本文基于核稀疏多元逻辑回归分类误差的统计建模分析,提出一种联合核稀疏多元逻辑回归和正则化错误剔除的高光谱图像分类模型.提出的模型通过引入隐概率场,采取L1范数度量KSMLR分类误差的重尾特性建立数据保真项;利用全变差(Total Variation,TV)正则化度量隐概率场的局部空间光滑性.由Indian Pines和University of Pavia数据集等实测数据应用表明,该方法可以得到更鲁棒和更高的分类精度.

Abstract

Sparse multinomial logistic regression (SMLR) is an important supervised classification method for hyperspectral images (HSI). However, because the traditional SMLR based pixel-wise classifiers only use the spectral signatures, the good robustness and high classification accuracy are hardly achieved with a small number of samples without considering the spatial information of HSI. By using the kernel tricks, the kernel sparse multinomial logistic regression (KSMLR) method can partly overcome this limitation, however the resulted misclassification errors are still expected to be further reduced. According to the statistical analysis of classification errors resulted in KSMLR, we propose a novel two stage framework which combines KSMLR and error rejection for HSI classification. The proposed model, named KSMRL-TVL1, adopts the L1 norm to measure the heavy-tailed property of the classification errors so as to build the data fidelity term, and uses the total variation (TV) regularization term to measure the local spatial smoothness of the hidden probability field. The experiments on Indian Pines dataset and University of Pavia dataset show that the proposed method can better improve the robustness and classification accuracy.

关键词

高光谱 / 图像分类 / 核稀疏多元逻辑回归 / 错误剔除

Key words

hyperspectral image / image classification / kernel sparse multinomial logistic regression / error rejection

引用本文

导出引用
徐金环, 沈煜, 刘鹏飞, 肖亮. 联合核稀疏多元逻辑回归和TV-L1错误剔除的高光谱图像分类算法[J]. 电子学报, 2018, 46(1): 175-184. https://doi.org/10.3969/j.issn.0372-2112.2018.01.024
XU Jin-huan, SHEN Yu, LIU Peng-fei, XIAO Liang. Hyperspectral Image Classification Combining Kernel Sparse Multinomial Logistic Regression and TV-L1 Error Rejection[J]. Acta Electronica Sinica, 2018, 46(1): 175-184. https://doi.org/10.3969/j.issn.0372-2112.2018.01.024
中图分类号: TP751   

参考文献

[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,2006.166-238. TONG Qing-xi,ZHANG Bing,ZHENG Lan-fen.Hyperspectral Remote Sensing[M].Beijing:Higher Education Press,2006.166-238.(in Chinese)
[2] 吴泽彬,韦志辉,孙乐,等.基于迭代加权L1正则化的高光谱混合像元分解[J].南京理工大学学报,2011,35(4):431-435. WU Ze-Bin,WEI Zhi-hui,SUN Le,et al.Hyperspectral unmixing based on iterative weighted L1 regularization[J].Journal of Nanjing University of Science and Technology,2011,35(4):431-435.(in Chinese)
[3] 宋相法,焦李成.基于稀疏表示及光谱信息的高光谱遥感图像分类[J].电子与信息学报,2012,34(2):268-272. SONG Xiang-fa,JIAO Li-cheng.Classification of hyperspectral remote sensing image based on sparse representation and spectral information[J].Journal of Electronics and Information Technology,2012,34(2):268-272.(in Chinese)
[4] DU Bo,ZHANG Liang-pei.Random-selection-based anomaly detector for hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(5):1578-1589.
[5] MELGANI F,BRUZZONE L.Classification of hyperspectral remote sensing images with support vector machines[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(8):1778-1790.
[6] BOHNING D.Multinomial logistic regression algorithm[J].Annals of the Institute of Statistical Mathematics,1992,44(1):197-200.
[7] CHEN Y,NASRABADI N M,TRAN T D.Hyperspectral image classification using dictionary based sparse representation[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(10):3973-3985.
[8] KRISHNAPURAM B,CARIN L,FIGUEIREDO M A T,Hartemink A J.Sparse multinomial logistic regression:fast algorithms and generalization bounds[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(6):957-968.
[9] BIOUCAS-DIAS J M,FIGUEIREDO M.Logistic regression via variable splitting and augmented lagrangian tools[R].Instituto Superior T'ecnico,TULisbon,2009.
[10] 孙乐,吴泽彬,冯灿,等.一种新的两分类器融合的空谱联合高光谱分类方法[J].电子学报,2015,43(11):2210-2217. SUN L,WU Ze-bin,FENG Can,et al.A novel two-classifier fusion method for spectral-spatial hyperspectral classification[J].Acta Electronica Sinica,2015,43(11):2210-2217.(in Chinese)
[11] GURRAM P,KWON H.Contextual SVM Using Hilbert Space Embedding for Hyperspectral Classification[J].IEEE Geoscience and Remote Sensing Letters,2013,10(5):1031-1035.
[12] 倪鼎,马洪兵.基于近邻协同的高光谱图像谱-空联合分类[J].自动化学报,2015,41(2):273-284. NI Ding,MA Hong-bing.Spectral-spatial classification of hyperspectral images based on neighborhood collaboration[J].Acta Automatica Sinica,2015,41(2):273-284.(in Chinese)
[13] CAMPS-VALLS G,GOMEZ-CHOVA L,MUNOZ-MARI J,et al.Composite kernels for hyperspectral image classification[J].IEEE Geoscience & Remote Sensing Letters,2006,3(1):93-97.
[14] DU Bo,ZHANG Liang-pei,ZHANG Le-fei,et al.A discriminative manifold learning based dimension reduction method for hyperspectral classification[J].International Journal of Fuzzy Systems,2012,14(2):272-277.
[15] SHI Qian,ZHANG Liang-pei,DU Bo.Semisupervised discriminative locally enhanced alignment for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(9):4800-4815.
[16] HUANG Xin,LU Qi-kai,ZHANG Liang-pei,et al.New postprocessing methods for remote sensing image classification:a systematic study[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(11):7140-7159.
[17] TARABALKA Y,FAUVEL M,CHANUSSOT J,et al.SVM-and MRF-based method for accurate classification of hyperspectral images[J].IEEE Geoscience and Remote Sensing Letters,2010,7(4):736-740.
[18] LI J,BIOUCAS-DIAS J M,PLAZA A.Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(11):4085-4098.
[19] LI J,BIOUCAS-DIAS J M,PLAZA A.Spectral-spatial hyperspectral image segmentation using subspace multinomial logistic regression and Markov random fields[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(3):809-823.
[20] ZHANG Bing,LI Shan-shan,JIA Xiu-ping,et al.Adaptive Markov random field approach for classification of hyperspectral imagery[J].IEEE Geoscience and Remote Sensing Letters,2011,8(5):973-977.
[21] SUN Le,WU Ze-bin,LIU Jian-jun,et al.Supervised spectral-spatial hyperspectral image classification with weighted Markov random fields[J].IEEE Transactions on Geoscience and Remote Sensing,2014,53(3):1490-1503.
[22] IORDACHE M D,BIOUCAS-DIAS J M,PLAZA A.Total variation spatial regularization for sparse hyperspectral unmixing[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(11):4484-4502.
[23] ESSER E.Applications of Lagrangian-Based Alternating Direction Methods and Connections to Split Bregman[R].CAM Report,2009.
[24] GOLDSTEIN T,OSHER S.The split bregman method for L1-regularized problems[J].SIAM Journal on Imaging Sciences,2009,2(2):323-343.
[25] WU Chun-lin,TAI Xue-cheng.Augmented Lagrangian method,dual methods,and split Bregman iteration for ROF,vectorial TV,and high order models[J].SIAM Journal on Imaging Sciences,2010,3(3):300-339.
[26] IORDACHE M D,BIOUCAS-DIAS J M,PLAZA A.Total variation spatial regularization for sparse hyperspectral unmixing[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(11):4484-4502.
[27] CHEN Y,NASRABADI N M,TRAN T D.Hyperspectral image classification via kernel sparse representation[A].Processing of International Conference on Image Processing[C].Brussels,Belgium:IEEE Computer Society,2011.1233-1236.
[28] LI J,BIOUCAS-DIAS J M,PLAZA A.Exploiting spatial information in semi-supervised hyperspectral image segmentation[A].Proceedings of Hyperspectral Image and Signal Processing:Evolution in Remote Sensing[C].Reykjavik,Iceland:GRSS,2010.1-4.
[29] DU B,WANG Z,ZHANG L,et al.Exploring representativeness and informativeness for active learning[J].IEEE Transactions on Cybernetics,2017,47(1):14-26.

基金

国家自然科学基金 (No.61571230); 国家重点研发计划 (No.2016YFF0103604); 江苏省自然科学基金 (No.BK20161500); 江苏省333工程 (No.BRA2015345)
PDF(17470 KB)

1046

Accesses

0

Citation

Detail

段落导航
相关文章

/