改进的高光谱图像线性预测波段选择算法

通过波段选择可以显著提高高光谱遥感图像分类与解混的效率。提出了两种改进的线性预测（LP）波段选择方法，用图像的偏度或峰度度量波段信息量，结合互信息（MI）或K-L散度度量波段间的相似性，选择本身信息量大，且彼此间最不相似的两个波段作为初始波段，再通过改进的线性预测选择后续波段。噪声波段的存在会影响波段选择的效果，导致分类或解混精度低于预期。为了减弱噪声波段的不利影响，进一步提出噪声波段去除的方法，基于小波域的熵估计每波段的噪声，去除噪声较大的波段后进行波段选择。真实高光谱图像波段选择后分类和解混实验结果表明，改进的基于线性预测的波段选择方法能明显提高分类和解混的精度和效率，是一种有效的高光谱图像降维方法。

Abstract

Band selection can greatly increase the efficiency of classification and unmixing of hyperspectral image. Two modified linear-prediction (LP) band selection methods based on similarity are proposed, which measure the information amount of bands through Skewness or Kurtosis and measure the similarity of bands through mutual information (MI) or K-L (Kullback-Leibler) divergence. The least similar two bands with large information amount are selected as the initial two bands, and the rest bands are selected by modified linear prediction. However, the existence of noise bands will affect the result of band selection, making the accuracy of classification or unmixing lower than expected. In order to weaken the adverse effect of noise bands, further efforts are made to estimate the noise of every band through wavelet entropy and remove the bands with considerable noise before band selection. The experiments of classification and unmixing after band selection for real hyperspectral images indicate that linear prediction based band selection can greatly increase the accuracy and efficiency of classification and unmixing , and it is an effective dimensionality reduction method for hyperspectral image.

参考文献

[1] C-I Chang. Hyperspectral Imaging: Techniques for Spectral Detection and Classification［M］. New York: Plenum, 2003.

[2] A R Webb. 统计模式识别(第二版)［M］. 王萍, 杨培龙译. 北京. 电子工业出版社, 2004.

A R Webb. Statistical Pattern Recognition (2nd edition) ［M］. Wang Ping, Yang Peilong Transl.. Beijing: Electronic Industry Press, 2004.

[3] 汤国安, 张友顺, 刘咏梅. 遥感数字图像处理［M］. 北京: 科学出版社, 2004.

Tang Guoan, Zhang Youshun, Liu Yongmei. Remote Sensing Digital Image Processing [M]. Beijing: Science press, 2004.

[4] J H Friedman, J W Tukey. A projeetion pursuit algorithm for exploratory data analysis［J］. IEEE Trans ComPuters, 1974, 23(9): 881-889.

[5] S Serpico, L Bruzzone. A new search algorithm for featureselection in hyperspectral remote sensing images［J］ . IEEE Trans Geosci Remote Sens, 2001, 39(7): 1360-1367.

[6] F Melgani, L Bruzzone. Classification of hyperspectral remote sensing images with support vector machines［J］. IEEE Trans Geosci Remote Sens, 2004, 42(8): 1778-1790.

[7] 苑津莎, 赵振兵, 高强, 等. 红外与可见光图像配准研究现状与展望 [J]. 激光与红外, 2009, 39(7): 693-699.

Yuan Jinsha, Zhao Zhenbing, Gao Qiang, et al.. Review and prospect on infrared /visible image registration［J］. Laser & Infrared, 2009, 39(7): 693-699.

[8] 杨金红. 高光谱遥感数据最佳波段选择方法研究［D］. 南京: 南京信息工程大学, 2005.

Yang Jinhong. Optimal Band Selection Methods of Hyperspectral Remote Sensing Data ［D］. Nanjing: Nanjing University of Information Science and Technology, 2005.

[9] 王国明, 孙立新. 高光谱遥感影像优化分类波段选择［J］. 东北测绘, 1999, 22(4): 21-23.

Wang Guoming, Sun Lixin. Wareband selection in optimized classification of high-spectrum RS imagery ［J］. Northeast of Surveying and Mapping, 1999, 22(4): 21-23.

[10] 张亚梅. 地物反射波谱特征及高光谱成像遥感［J］. 光电技术应用, 2008, 23(5): 6-11.

Zhang Yamei. Spectrum characteristics of surface features reflection and high spectral imaging remote sensing ［J］. Electro-Optic Technology Application, 2008, 23 (5): 6-11.

[11] P W Mausel, W J Kramver, J K Lee. Optimum band selection for supervised classification of multispectral data［J］ . Photogrammetric Engineering and Remote Sensing, 1990, 56: 55-60.

[12] Cheng Hong, Wang Zhiqiang, Zhang Yaoyu. Research on geometric rectification of aerial images［J］. J Northeast Normal University, 2009, 41(3): 50-54.

[13] 吴超, 吴一全. 基于混沌粒子群优化投影寻踪的高光谱图像目标检测［J］. 光学学报, 2011, 31(12): 1211003.

Wu Chao, Wu Yiquan. Target detection in hyperspectral image using projection pursuit based on chaotic particle swarm optimization ［J］. Acta Optica Sinica, 2011, 31(12): 1211003.

[14] Qian Du, He Yang. Similarity-based unsupervised band selection for hyperspectral image analysis［J］. IEEE Geoscience and Remote Sensing Letters, 2008, 5(4): 564-568.

[15] 赵选民, 徐伟, 师义民, 等. 数理统计 [M]. 北京: 北京科学出版社, 2003.

Zhao Xuanmin, Xu Wei, Shi Yimin, et al.. Mathematical Statistics ［M］. Beijing: Beijing Science and Technology Press, 2003.

[16] C Cachin. An information theoretic model for steganography［C］. LNCS: 2nd Int′l Workshop on Information Hiding, 1998, 1525: 306-318.

[17] T M Cover, J A Thomas. Elements of Information Theory［M］. New York: Wiley-Interscience, 1991.

[18] Q Du. Band selection and its impact on target detection and classification in hyperspectral image analysis［C］. IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003: 374-377.

[19] S Jia, Z Ji, Y Qian, et al.. Unsupervised band selection for hyperspectral imagery classification without mannual band removal［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(2): 531-543.

[20] 陈丛, 卢启鹏, 彭忠琦. 基于NLMS自适应滤波的近红外光谱去噪处理方法研究［J］. 光学学报, 2012, 32(5): 0530001.

Chen Cong, Lu Qipeng, Peng Zhongqi. Preprocessing methods of near-infrared spectrum based on NLMS adaptive filtering［J］. Acta Optica Sinica, 2012, 32(5): 0530001.

[21] 付强, 相里斌, 景娟娟. 基于多光谱遥感成像链模型的系统信噪比分析［J］. 光学学报, 2012, 32(2): 0211001.

Fu Qiang, Xiangli Bin, Jing Juanjuan. System signal-to-noise ratio analysis based on imaging chain model in multispectral remote sensing ［J］. Acta Optica Sinica, 2012, 32(2): 0211001.

[22] 刘雪松, 葛亮, 王斌. 基于最大信息量的高光谱遥感图像无监督波段选择方法［J］. 红外与毫米波学报, 2012, 31(2): 166-176.

Liu Xuesong, Ge Liang, Wang Bin. An unsupervised band selection algorithm for hyperspectral imagery based on maximal information ［J］. Infrared and Millimeter Wave Technology, 2012, 31(2): 166-176.

[23] 李天翼, 王明辉, 常化文, 等. 基于熵检测的图像噪声方差小波域估计［J］. 北京邮电大学学报, 2011, 34(5): 1-5.

Li Tianyi, Wang Minghui, Chang Huawen, et al.. An entropy-based estimation of noise variance in wavelet domain ［J］. Journal of Beijing University of Posts and Telecommunications, 2011, 34(5): 1-5.

[24] D Donoho, I M Johnstone. Ideal spatial adaptation by wavelet shrinkage［J］. Biometrika, 1994, 81(3): 425-455.

[25] Y Zhou, X Li, J Cui. High-efficiency hyperspectral unmixing based on band selection [C]. Third Global Congress on Intelligent Systems, 2012: 140-143.

[26] 高连如, 张兵, 张霞. 基于局部标准差的遥感图像噪声评估方法研究［J］. 遥感学报, 2007, 11(2): 201-208.

Gao Lianru, Zhang Bing, Zhang Xia. Study on the method for estimating the noise in remote sensing images based on local standard deviations ［J］. J Remote Sensing, 2007, 11(2): 201-208.

[27] C E Shannon. A mathematical theory of communication ［J］. Bell System Tech Journal, 1948, 27: 379-423, 623-656.

[28] 林哲民, 康学雷, 张立明. 小波域中进行图像噪声方差估计的EM方法［J］. 红外与毫米波学报, 2001, 20(3): 199-202.

Lin Zhemin, Kang Xuelei, Zhang Liming. EM algorithm for estimating the noise deviation of the image in the wavelet domain ［J］. Infrared and Millimeter Wave Technology, 2001, 20(3): 199-202.

[29] AVIRIS NW Indiana′s Indian Pines 1992 Data Set. ［Online］. Available:https://engineering.purdue.edu/biehl/MultiSpec/hyperspectral.html.

[30] F Melgani, L Bruzzone. Classification of hyperspectral remote sensing images with support vector machines［J］. IEEE Trans Geosci Remote Sens, 2004, 42(8): 1778-1790.

[31] 赵春晖, 齐滨, 张燚. 基于改进型相关向量机的高光谱图像分类［J］. 光学学报, 2012, 32(8): 0828004.

Zhao Chunhui, Qi Bin, Zhang Yan. Hyperspectral image classification based on variational relevance vector machine ［J］. Acta Optica Sinica, 2012, 32(8): 0828004.

[32] 崇伟, 沙奕卓, 行鸿彦, 等. 一种基于支持向量机回归的旋转遮光带日射表散射辐照度修正新算法［J］. 光学学报, 2012, 32(1): 0112001.

Chong Wei, Sha Yizhuo, Xing Hongyan, et al.. A new correction algorithm for diffuse irradiance measured with rotating shadow-band pyranometer based on support vector regression ［J］. Acta Optica Sinica, 2012, 32(1): 0112001.

[33] T Cover, P Hart. Nearest neighbor pattern classification［J］. IEEE Trans Inf Theory, 1967, 13(1): 21-27.

[34] J P Hoffbeck, D A Landgrebe. Classification of remote sensing images having high spectral resolution［J］. Remote Sensing of Environment, 1996, 57(3): 119-126.

[35] D D Lee, H S Seung. Learning the parts of objects by non-negative matrix factorization［J］. Nature, 1999, 401(6755): 788-791.

周杨, 厉小润, 赵辽英. 改进的高光谱图像线性预测波段选择算法[J]. 光学学报, 2013, 33(8): 0828002. Zhou Yang, Li Xiaorun, Zhao Liaoying. Modified Linear-Prediction Based Band Selection for Hyperspectral Image[J]. Acta Optica Sinica, 2013, 33(8): 0828002.

改进的高光谱图像线性预测波段选择算法

关于本站 Cookie 的使用提示

全站搜索

改进的高光谱图像线性预测波段选择算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索