基于空间-光谱特征和稀疏表达的高光谱图像分类算法

摘要
参考文献
相关文章

全文: PDF (873 KB) HTML ( KB) 输出: BibTeX | EndNote (RIS) 背景资料

摘要针对传统的高光谱数据分类方法分类精度不高、没有充分地利用空间信息等缺陷，提出一种基于Gabor空间纹理特征(Gabor spatial texture features)及无参数加权光谱特征(Nonparametric weighted spectral features)和稀疏表达分类(Sparse representation classification)的高光谱图像分类算法，可以简写为 Gabor-NWSF和SRC，即GNWSF-SRC。所提出的GNWSF-SRC分类方法首先通过融合高光谱的Gabor空间特征和无参数加权光谱特征来更好地描述高光谱图像，然后通过其进行稀疏表达，最终通过对比其重构误差获得分类结果。在训练集比例不同的情况下，用所提出的方法对两组典型的高光谱数据进行处理，理论研究和仿真结果表明：与传统的分类方法相比，所提出算法能够提高分类精度、Kappa系数等，取得了较好的分类效果。

	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
	杨京辉
	王立国
	钱晋希

关键词：高光谱分类稀疏表达空间特征光谱特征

Abstract： To minimize the low classification accuracy and low utilization of spatial information in traditional hyperspectral image classification methods, we propose a new hyperspectral image classification method, which is based on the Gabor spatial texture features and nonparametric weighted spectral features, and the sparse representation classification method (Gabor–NWSF and SRC), abbreviated GNWSF–SRC. The proposed (GNWSF–SRC) method first combines the Gabor spatial features and nonparametric weighted spectral features to describe the hyperspectral image, and then applies the sparse representation method. Finally, the classification is obtained by analyzing the reconstruction error. We use the proposed method to process two typical hyperspectral data sets with different percentages of training samples. Theoretical analysis and simulation demonstrate that the proposed method improves the classification accuracy and Kappa coefficient compared with traditional classification methods and achieves better classification performance.

Key words： Hyperspectral classification sparse representation spatial features spectral features

收稿日期: 2014-04-26;

基金资助:

本研究由国家自然科学基金（编号：61275010）、教育部博士点基金(编号 No. 20132304110007)、黑龙江省自然科学基金（编号：F201409）、中央高校基本科研业务费重大项目（编号：HEUCFD1410）联合资助。

引用本文:

杨京辉,王立国,钱晋希. 基于空间-光谱特征和稀疏表达的高光谱图像分类算法[J]. 应用地球物理, 2014, 11(4): 489-499.

YANG Jing-Hui,WANG Li-Guo,QIAN Jin-Xi. Hyperspectral image classification based on spatial and spectral features and sparse representation[J]. APPLIED GEOPHYSICS, 2014, 11(4): 489-499.

[1]	Bau, T. C., Sarkar, S., and Healey, G., 2010, Hyperspectral Region Classification Using a Three-Dimensional Gabor Filterbank: IEEE Geoscience and Remote Sensing Letters, 48(9), 2457-3463.
[2]	Bo, Y. C., and Wang, J. F.,,2005, Assessment on Uncertainty in Remotely Sensed Data Classification: Progresses, Problems and Prospects: Advances in Earth Science, 20(11), 1218-1225.
[3]	Cavalli, R. M., Licciardi, G. A., and Chanussot, J., 2013, Archaeological Structures Using Nonlinear Principal Component Analysis Applied to Airborne Hyperspectral Image: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2), 659-669.
[4]	Chen, G. Y., and Qian, S. E., 2011, Denoising of Hyperspectral Imagery Using Principal Component Analysis and Wavelet Shrinkage: IEEE Transactions on Geoscience and Remote Sensing, 49(3), 973-980.
[5]	Chen, Y., Nasrabadi, N. M., and Tran, T. D., 2011a, Sparse Representation for Target Detection in Hyperspectral Imagery: IEEE Journal of Selected Topics in Signal Processing, 5(3), 629-640.
[6]	Chen, Y., Nasrabadi, N. M., and Tran, T. D., 2011b, Hyperspectral Image Classification Using Dictionary-Based Sparse Representation: IEEE Transactions on Geoscience and Remote Sensing, 49(10), 3973-3985.
[7]	Clausi, D. A., and Jernigan, M. E., 2000, Designing Gabor filters for optimal texture separability: Pattern Recognition, 33,1835-1849.
[8]	Dunn, D., Higgins, W. E., and Wakeley, J., 1994, Texture Segmentation Using 2-D Gabor Elementary Functions: IEEE Transactions on Paitern Analysis and Machine Intelligence, 16(2), 130-149.
[9]	Foody, G. M., 2002, Status of Land Cover Classification Accuracy Assessment: Remote Sensing of Environment, 80, 185-201.
[10]	Hebiri, M., and Lederer, J., 2013, How Correlations Influence Lasso Prediction: IEEE Transactions on Information Theory, 59(3), 1846-1854.
[11]	Hofleitner, A., Rabbani, T., and Ghaoui, L. E., 2013, Online Homotopy Algorithm for a Generalization of the LASSO: IEEE Transactions on Automatic Control, 58(12), 3175-3179.
[12]	Huang, H. Y., and Kuo, B. C., 2010, Double Nearest Proportion Feature Extraction for Hyperspectral-Image Classification: IEEE Transactions on Geoscience and Remote Sensing, 48(11), 4034-4046.
[13]	Hung, C. C., Kulkarni, S., and Kuo, B. C., 2011, A New Weighted Fuzzy C-Means Clustering Algorithm for Remotely Sensed Image Classification: IEEE Journal of Selected Topics in Signal Processing, 5(3), 543-553.
[14]	Iordache, D., Bioucas-Dias, J. M., and Plaza, A., 2012, Total variation spatial regularization for sparse hyperspectral unmixing: IEEE Transactions on Geoscience and Remote Sensing, 50(11), 4482-4502.
[15]	Jain, A. K., and Farrokhnia, F., 1991, Unsupervised texture segmentation using Gabor filters: Pattern Recognition, 24(12), 1167-1186.
[16]	Kuo, B. C., Ho, H. H., and Li, C. H., 2014, A Kernel-Based Feature Selection Method for SVM With RBF Kernel for Hyperspectral Image Classification: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(1), 317-326.
[17]	Kuo, B. C., and Landgrebe, D. A., 2002a, Hyperspectral data classification using nonparametric weighted feature extraction: IEEE International Geoscience and Remote Sensing Symposium, 3, 1428-1430.
[18]	Kuo, B. C., and Landgrebe, D. A., 2002b, A robust classification procedure based on mixture classifiers and nonparametric weighted feature extraction: IEEE Transactions on Geoscience and Remote Sensing, 40(11), 2486-2494.
[19]	Kuo, B. C., and Landgrebe, D. A., 2004, Nonparametric Weighted Feature Extraction for Classification: IEEE Transactions on Geoscience and Remote Sensing, 42(5), 1096-1105.
[20]	Kuo, B. C., Li, C. H., and Yang, J. M.. 2009, Kernel Nonparametric Weighted Feature Extraction for Hyperspectral Image Classification: IEEE Transactions on Geoscience and Remote Sensing, 47(4),1139-1155.
[21]	Mairal, J., and Bach, F., 2010, Online Learning for Matrix Factorization and Sparse Coding: Journal of Machine Learning Research, 11(1), 19-60.
[22]	Melgani, F., and Bruzzone, L., 2004, Classification of Hyperspectral Remote Sensing Images With Support Vector Machines: IEEE Transactions on Geoscience and Remote Sensing, 42(8), 1778-1790.
[23]	Plaza, A., Benediktsson, J. A., and Boardman, J. W., 2009, Recent advances in techniques for hyperspectral image processing: Remote Sensing of Environment, 113, s110-s122.
[24]	Qian, Y. T., and Ye, M. C., 2013, Hyperspectral Imagery Restoration Using Nonlocal Spectral-Spatial Structured Sparse Representation With Noise Estimation: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2), 499-515.
[25]	Ren, C. X., Dai, D. Q., and Li, X. X., 2014, Band-Reweighed Gabor Kernel Embedding for Face Image Representation and Recognition: IEEE Transactions on Image Processing, 23(2), 725-740.
[26]	Samiappan, S., Prasad, S., and Bruce, L. M., 2013, Non-Uniform Random Feature Selection and Kernel Density Scoring With SVM Based Ensemble Classification for Hyperspectral Image Analysis: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2), 792-800.
[27]	Shen, L. L., Zhu, Z. X., and Jia, S., 2013, Discriminative Gabor Feature Selection for Hyperspectral Image Classification: IEEE Geoscience and Remote Sensing Letters, 10(1), 29-33.
[28]	Song, B. Q., Li, J., and Mura, M. D., 2014, Remotely Sensed Image Classification Using Sparse Representations of Morphological Attribute Profiles: IEEE Transactions on Geoscience and Remote Sensing, 52(8), 5122-5136.
[29]	Steele, B. M., Winne, J. C., and Redmond, R. L., 1998, Estimation and Mapping of Misclassification Probabilities for Thematic Land Cover Maps: Remote Sensing of Environment, 66, 192-202.
[30]	Wang, L. G., Liu, D. F., and Zhao, L., 2013, A Color Visualization Method Based on Sparse Representation of Hyperspectral Imagery: Applied Geophysics, 10(2), 210-221.
[31]	Wright, J., and Yang, A. Y., 2009, Arvind Ganesh, Robust Face Recognition via Sparse Representation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(2), 210-227.
[32]	Xing, X. W., Ji, K. F., and Zou, H. X., 2013, Ship Classification in TerraSAR-X Images With Feature Space Based Sparse Representation: IEEE Geoscience and Remote Sensing Letters, 10(6), 1562-1566.
[33]	Yang, J. C., Wright, J., and Huang, T. S., 2010, Image Super-Resolution Via Sparse Representation: IEEE Transactions on Image Processing, 19(11), 2861-2873.
[34]	Zhang, E., Zhang, X. G., and Yang, S. Y., 2014, Improving Hyperspectral Image Classification Using Spectral Information Divergence: IEEE Geoscience and Remote Sensing Letters, 11(1), 249-253.
[35]	Zhang, L. F., Zhang, L. P., and Tao, D. C., 2011, A Multifeature Tensor for Remote-Sensing Target Recognition: IEEE Geoscience and Remote Sensing Letters, 8(2), 374-378.
[36]	Zhang, L. F., Zhang, L. P., and Tao, D. C., 2012, On Combining Multiple Features for Hyperspectral Remote Sensing Image Classification: IEEE Transactions on Geoscience and Remote Sensing, 50(3), 879-893.

[1]	王立国, 刘丹凤, 赵亮. 基于高光谱图像稀疏表示的彩色可视化模型[J]. 应用地球物理, 2013, 10(2): 210-221.
[2]	Mohammad Ehsan Hekmatian, Vahid E. Ardestani, Mohammad Ali Riahi, Ayyub Memar Koucheh Bagh, and Jalal Amini. 利用支持向量分类（SVC）估算断层深度和特征选择[J]. 应用地球物理, 2013, 10(1): 88-96.