面向高光谱图像分类的半监督空谱判别分析

侯榜焕; 王锟; 姚敏立; 贾维敏; 王榕

doi:10.11947/j.AGCS.2017.20170121

测绘学报 >

2017 , Vol. 46 >Issue 9: 1098 - 1106

DOI: https://doi.org/10.11947/j.AGCS.2017.20170121

摄影测量学与遥感

面向高光谱图像分类的半监督空谱判别分析

侯榜焕 ,
王锟 ,
姚敏立 ,
贾维敏 ,
王榕

展开

1. 火箭军工程大学信息工程系, 陕西西安 710025;
2. 国家计算机网络应急技术处理协调中心, 北京 100029

侯榜焕(1985-),男,博士生,研究方向为信号处理、机器学习、高光谱图像处理等。E-mail:chinayouth001@aliyun.com

收稿日期: 2017-03-20

修回日期: 2017-07-24

网络出版日期: 2017-10-12

基金资助

国家自然科学基金青年科学基金（61401471）；中国博士后科学基金（2014M562636）

收起

Semi-supervised Spatial-spectral Discriminant Analysis for Hyperspectral Image Classification

HOU Banghuan ,
WANG Kun ,
YAO Minli ,
JIA Weimin ,
WANG Rong

Expand

1. Department of Information Engineering, Rocket Force Engineering University, Xi'an 710025, China;
2. National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing 100029, China

Received date: 2017-03-20

Revised date: 2017-07-24

Online published: 2017-10-12

Supported by

The Young Scientists Fund of the National Natural Science Foundation of China (No. 61401471);The China Postdoctoral Science Foundation(No. 2014M562636)

Fold

摘要

为充分利用高光谱图像蕴藏的空间信息提升分类精度，提出了面向高光谱图像分类的半监督空谱判别分析（S³DA）算法。考虑高光谱图像数据集的空间一致性，首先利用少量标记样本定义类内散度矩阵，保存数据集同类像元的光谱近邻结构；再利用无标记样本定义空间近邻像元散度矩阵，揭示像元间的空间近邻结构和地物的空间分布结构信息。S³DA既保持数据集在光谱域的可分性，又保存了无标记样本蕴藏的空间域近邻结构，增强了同类像元和空间近邻像元在投影子空间的聚集性，从而提升分类性能。在PaviaU和Indian Pines数据集的试验表明，总体分类精度分别达到81.50%和71.77%。与传统的光谱方法比较，该算法能有效提升高光谱图像数据集的地物分类精度。

关键词： 高光谱图像分类; 特征提取; 判别分析; 空谱联合; 半监督学习; 空间近邻

本文引用格式

侯榜焕 , 王锟 , 姚敏立 , 贾维敏 , 王榕 . 面向高光谱图像分类的半监督空谱判别分析[J]. 测绘学报, 2017 , 46(9) : 1098 -1106 . DOI: 10.11947/j.AGCS.2017.20170121

Abstract

In order to make full use of the spatial information embedded in the hyperspectral image to improve the classification accuracy, a semi-supervised spatial-spectral discriminant analysis (S³DA) algorithm for hyperspectral image classification is proposed. According to the spatial consistency property of hyperspectral image, the intra-class scatter matrix infered from a little labeled samples preserves the spectral similarity of the same class pixels, while the spatial local pixel scatter matrix defined by the unlabeled spatial neighbors uncovers the spatial-domain local pixel neighborhood structures and the ground objects detailed distribution. The S³DA method not only maintains the spectral-domain separability of the data set, but also preserves the spatial-domain local pixel neighborhood structure, which promotes the compactness of the same class pixels or the spatial neighbor pixels in the projected subspace and enhances the classification performance. The overall classification accuracies respectively reach 81.50% and 71.77% on the PaviaU and Indian Pines data sets. Compared with the traditional spectral methods, the proposed method can effectively improve ground objects classification accuracy.

Key words： hyperspectral image classification; feature extraction; discriminant analysis; spatial-spectral; semi-supervised learning; spatial neighbors

参考文献

[1] FAUVEL M,TARABALKA Y,BENEDIKTSSON J A,et al.Advances in Spectral-Spatial Classification of Hyperspectral Images[J].Proceedings of the IEEE,2013,101(3):652-675.
[2] 黄鸿,郑新磊.高光谱影像空-谱协同嵌入的地物分类算法[J].测绘学报,2016,45(8):964-972.DOI:10.11947/j.AGCS.2016.20150654. HUANG Hong,ZHENG Xinlei.Hyperspectral Image Land Cover Classification Algorithm Based on Spatial-spectral Coordination Embedding[J].Acta Geodaetica et Cartographica Sinica,2016,45(8):964-972.DOI:10.11947/j.AGCS.2016.20150654.
[3] 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.
[4] 骆仁波,皮佑国.有监督的邻域保留嵌入的高光谱遥感影像特征提取[J].测绘学报,2014,43(5):508-513.DOI:10.13485/j.cnki.11-2089.2014.0079. LUO Renbo,PI Youguo.Supervised Neighborhood Preserving Embedding Feature Extraction of Hyperspectral Imagery[J].Acta Geodaetica et Cartographica Sinica,2014,43(5):508-513.DOI:10.13485/j.cnki.11-2089.2014.0079.
[5] 李志敏,张杰,黄鸿,等.面向高光谱图像分类的半监督Laplace鉴别嵌入[J].电子与信息学报,2015,37(4):995-1001. LI Zhimin,ZHANG Jie,HUANG Hong,et al.Semi-Supervised Laplace Discriminant Embedding for Hyperspectral Image Classification[J].Journal of Electronics & Information Technology,2015,37(4):995-1001.
[6] JACKSON J E.A User's Guide to Principal Components[M].New York:A Wiley-Interscience Publication,1992.
[7] BANDOS T V,BRUZZONE L,CAMPS-VALLS G.Classification of Hyperspectral Images with Regularized Linear Discriminant Analysis[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(3):862-873.
[8] BELKIN M,NIYOGI P.Laplacian Eigenmaps for Dimensionality Reduction and Data Representation[J].Neural Computation,2003,15(6):1373-1396.
[9] ROWEIS S T,SAUL L K.Nonlinear Dimensionality Reduction by Locally Linear Embedding[J].Science,2000,290(5500):2323-2326.
[10] HE Xiaofei,NIYOGI P.Locality Preserving Projections[C]//Advances in Neural Information Processing Systems.Cambridge:MIT Press,2004(16):153-160.
[11] HE Xiaofei,CAI Deng,YAN Shuicheng,et al.Neighborhood Preserving Embedding[C]//Proceedings of the 10th IEEE International Conference on Computer Vision.Beijing:IEEE,2005:150-156.
[12] CAI Deng,HE Xiaofei,HAN Jiawei.Semi-supervised Discriminant Analysis[C]//Proceedings of the 11th IEEE International Conference on Computer Vision.Rio de Janeiro:IEEE,2007:1-7.
[13] SUGIYAMA M,IDÉ T,NAKAJIMA S,et al.Semi-supervised Local Fisher Discriminant Analysis for Dimensionality Reduction[J].Machine Learning,2010,78(1-2):35-61.
[14] LIAO Wenzhi,PIZURICA A,SCHEUNDERS P,et al.Semisupervised Local Discriminant Analysis for Feature Extraction in Hyperspectral Images[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(1):184-198.
[15] LUO Renbo,LIAO Wenzhi,HUANG Xin,et al.Feature Extraction of Hyperspectral Images with Semisupervised Graph Learning[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(9):4389-4399.
[16] LI Jun,MARPU P R,PLAZA A,et al.Generalized Composite Kernel Framework for Hyperspectral Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(9):4816-4829.
[17] KANG Xudong,LI Shutao,BENEDIKTSSON J A.Spectral-Spatial Hyperspectral Image Classification with Edge-preserving Filtering[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(5):2666-2677.
[18] TARABALKA Y,BENEDIKTSSON J A,CHANUSSOT J.Spectral-spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(8):2973-2987.
[19] LI Jun,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] WEN Jinhua,FOWLER J E,HE Mingyi,et al.Orthogonal Nonnegative Matrix Factorization Combining Multiple Features for Spectral-Spatial Dimensionality Reduction of Hyperspectral Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(7):4272-4286.
[21] KANG Xudong,LI Shutao,BENEDIKTSSON J A.Feature Extraction of Hyperspectral Images with Image Fusion and Recursive Filtering[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(6):3742-3752.
[22] XIA Junshi,BOMBRUN L,ADALI T,et al.Spectral-Spatial Classification of Hyperspectral Images Using ICA and Edge-Preserving Filter via an Ensemble Strategy[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(8):4971-4982.
[23] 魏峰,何明一,梅少辉.空间一致性邻域保留嵌入的高光谱数据特征提取[J].红外与激光工程,2012,41(5):1249-1254. WEI Feng,HE Mingyi,MEI Shaohui.Hyperspectral Data Feature Extraction Using Spatial Coherence Based Neighborhood Preserving Embedding[J].Infrared and Laser Engineering,2012,41(5):1249-1254.
[24] 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.
[25] LUNGA D,PRASAD S,CRAWFORD M M,et al.Manifold-Learning-based Feature Extraction for Classification of Hyperspectral Data:A Review of Advances in Manifold Learning[J].IEEE Signal Processing Magazine,2014,31(1):55-66.
[26] YUAN Haoiang,TANG Yuanyan,LU Yang,et al.Spectral-Spatial Classification of Hyperspectral Image Based on Discriminant Analysis[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(6):2035-2043.
[27] ZHOU Yicong,PENG Jiangtao,CHEN C L P.Dimension Reduction Using Spatial and Spectral Regularized Local Discriminant Embedding for Hyperspectral Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(2):1082-1095.
[28] GAO Quanxue,MA Jingjie,ZHANG Hailin,et al.Stable Orthogonal Local Discriminant Embedding for Linear Dimensionality Reduction[J].IEEE Transactions on Image Processing,2013,22(7):2521-2531.
[29] WEINBERGER K Q,SAUL L K.An Introduction to Nonlinear Dimensionality Reduction by Maximum Variance Unfolding[C]//Proceedings of the 21st Association on Advances in Artificial Intelligence.Boston,MA:AAAI,2006:1683-1686.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献