电光与控制, 2016, 23 (4): 48, 网络出版: 2016-09-12  

基于图像欧式距离和拉普拉斯特征映射的端元提取算法

Endmember Extraction Based on Image Euclidean Distance and Laplacian Eigenmaps
作者单位
南阳理工学院电子与电气工程学院,河南 南阳473004
摘要
由于多重反射和散射,高光谱图像中的混合像元实际上是非线性光谱混合。传统的端元提取算法是以线性光谱混合模型为基础,因此提取精度不高。针对高光谱图像的非线性结构,提出了基于图像欧氏距离非线性降维的高光谱遥感图像端元提取方法。该方法结合高光谱数据的物理特性,将图像欧氏距离引入拉普拉斯特征映射进行非线性降维以更好地去除高光谱数据集中冗余的空间信息和光谱维度信息,然后对降维后的数据利用寻找最大单形体体积的方法提取端元。真实高光谱数据实验表明,提出的方法对高光谱图像端元提取具有良好的效果,性能优于线性降维的主成份分析算法和原始的拉普拉斯特征映射算法。
Abstract
Mixed pixel in hyperspectral image is actually nonlinear mixing of endmembers,which is caused by multiple reflectances and scattering.The traditional endmember extraction algorithms based on linear spectral mixture model perform poorly in finding the correct endmembers.Considering the physical characters of hyperspectral imagery,a new method is proposed to introduce image Euclidean distance into Laplacian Eigenmaps for nonlinear dimension reduction.The proposed method can discard efficiently the redundant information from both the spectral and spatial dimensions.Endmembers are extracted by looking for the largest simplex volume from low-dimensional space.Experimental results demonstrate that the proposed method outperforms the PCA and Laplacian Eigenmaps algorithm.
参考文献

[1] KESHAVA N,MUSTARD J F.Spectral unmixing[J].IEEE Signal Processing Magazine,2002,19(1):44-57.

[2] PLAZA A,MARTINEZ P,PREZ R,et al.A quantitative and comparative analysis of endmember extraction algorithms from hyperspectral data[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(3):650-663.

[3] NEVILLE R A,STAENZ K,SZEREDI T,et al.Automatic endmember extraction from hyperspectral data for mineral exploration[C]//Proceedings of 21st Canadian Symposium Remote Sensing,Ottawa.1999:21-24.

[4] JIA S,QIAN Y.Constrained nonnegative matrix factorization for hyperspectral unmixing[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(1):161-173.

[5] BIOUCAS-DIAS J M,PLAZA A,DOBIGEON N,et al.Hyperspectral unmixing overview:geometrical,statistical,and sparse regression-based approaches[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012,5(2):354-379.

[6] BACHMANN C M,AINSWORTH T L,FUSINA R A.Exploiting manifold geometry in hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing, 2005,43(3):441-454.

[7] 刘钦龙,焦斌亮,刘立.基于改进的BP神经网络模型的遥感图像分类方法研究[J].电光与控制, 2009,16(8):65-67.(LIU Q L,JIAO B L,LIU L.On remote sensing image classification method based on improved BP neural network model[J].Electronics Optics & Control, 2009,16(8):65-67.)

[8] 杜培军,王小美,谭琨,等.利用流形学习进行高光谱遥感影像的降维与特征提取[J].武汉大学学报:信息科学版, 2011,36(2):148-152.(DU P J,WANG X M, TAN K,et al.Dimensionality reduction and feature extraction from hyperspectral remote sensing imagery based on manifold learning[J].Geomatics and Information Science of Wuhan University,2011,36(2):148-152.)

[9] CHEN Y C,CRAWFORD M M,GHOSH J.Improved nonlinear manifold learning for land cover classification via intelligent landmark selection[C]//IEEE International Conference on Geoscience and Remote Sensing Symposium,Denver,2006:545-548.

[10] MA L,CRAWFORD M M,TIAN J.Anomaly detection for hyperspectral images based on robust locally linear embedding[J].Journal of Infrared,Millimeter,and Terahertz Waves,2010,31(6):753-762.

[11] HEYLEN,R,BURAZEROVIC D,SCHEUNDERS P.Non-linear spectral unmixing by geodesic simplex volume maximization[J].IEEE Journal of Selected Topics in Signal Processing,2011,5(3):534-542.

[12] BELKIN M,NIYOGI P.Laplacian eigenmaps and spectral techniques for embedding and clustering[J].Advances in Neural Information Processing Systems,2001:585-591.

[13] WANG L,ZHANG Y,FENG J.On the Euclidean distance of images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(8):1334-1339.

[14] 陈宏达,普晗晔,王斌,等.基于图像欧氏距离的高光谱图像流形降维算法[J].红外与毫米波学报,2013,32(5):450-455.(CHEN H D,PU H Y,WANG B,et al.Image Euclidean distance-based manifold dimensionality reduction algorithm for hyperspectral imagery[J].Journal Infrared and Millimeter Waves,2013,32(5):450-455.)

[15] WINTER M E.N-FINDR:an algorithm for fast autonomous spectral endmember determination in hyperspectral data[C]//SPIEs International Symposium on Optical Science,Engineering,and Instrumentation.International Society for Optics Engineering,Denver,1999:266-275.

[16] CHANG C I,DU Q.Estimation of number of spectrally distinct signal sources in hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(3):608-619.

[17] SWAYZE G,CLARK R N,KRUSE F,et al.Ground-tru-thing aviris mineral mapping at Cuprite,Nevada[C]//JPL publication,Summaries of the Third Annual JPL Airborne Geosciences Workshop,Volume 1:AVIRIS Workshop,1992:47-49.

[18] ZORTEA M,PLAZA A.Spatial preprocessing for endmember extraction[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(8):2679-2693.

[19] 马丽.基于流形学习算法的高光谱图像分类和异常检测[D].武汉:华中科技大学,2010.(MA L.Manifold learning methods for hyperspectral image classification and anomaly detection[D].Wuhan:Huazhong University of Science and Technology,2010.)

杨磊, 刘尚争. 基于图像欧式距离和拉普拉斯特征映射的端元提取算法[J]. 电光与控制, 2016, 23(4): 48. YANG Lei, LIU Shang-zheng. Endmember Extraction Based on Image Euclidean Distance and Laplacian Eigenmaps[J]. Electronics Optics & Control, 2016, 23(4): 48.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!