浏览全部资源
扫码关注微信
纸质出版日期： 2021-05-07 ，
扫 描 看 全 文
苏红军，顾梦宇.2021.高光谱遥感影像优化判别局部对齐特征提取.遥感学报，25（5）： 1055-1070
Su H J and Gu M Y. 2021. Feature extraction of hyperspectral remote sensing image based on optimized Discriminative Locality Alignment. National Remote Sensing Bulletin， 25（5）：1055-1070
目前，高光谱遥感特征提取方法往往因受到噪声的干扰而导致降维效果欠佳。近年来，判别局部对齐DLA（Discriminative Locality Alignment）由于可以处理非线性分布样本、保留局部判别信息，同时避免矩阵奇异性问题，受到了很多学者的关注；但该方法无法有效估计和减少噪声对高光谱遥感影像的影响。针对以上问题，本文提出了最小噪声判别局部对齐MDLA（Minimum-noise Discriminative Locality Alignment）的线性特征提取方法和核最小噪声判别局部对齐KMDLA（Kernel Minimum-noise Discriminative Locality Alignment）的非线性特征提取方法。充分利用最小噪声分离MNF（Minimum Noise Fraction）的去噪能力，将MNF与DLA算法结合提出了MDLA方法，该方法首先利用MNF对高光谱遥感影像进行降维，减少图像中的噪声，然后再在子空间进行DLA变换得到最终的投影数据。为提高样本分布的非线性判别能力，基于KMNF与DLA算法将核方法引入MDLA，提出了KMDLA方法，该方法首先通过KMNF将原始空间的数据映射到新的特征空间，然后在特征空间中进行DLA变换得到最终的投影数据。实验部分首先利用3组高光谱遥感数据对提出算法的性能进行评价，并与相关特征提取算法进行了对比分析，最后分析了图像噪声对不同降维方法性能的影响。结果表明：提出的算法对高光谱遥感影像特征提取效果较好，且可有效减少噪声对影像的影响并提升其分类准确度。
Discriminative Locality Alignment (DLA) is a linear feature extraction algorithm
which has exhibited effectiveness in many fields. The algorithm can deal with the nonlinearity of samples distribution
preserve discriminative information over local patches
and avoid the problem of matrix singularity in calculation. Generally
the PCA step is recommended for reducing noise. However
PCA extracts noise images with low order components
and bands with a small variance do not necessarily indicate poor image quality. To effectively reduce the influence of noise on DLA and further improve the accuracy of DLA in the feature extraction of hyperspectral remote sensing images
a linear feature extraction algorithm of MDLA and a nonlinear feature extraction algorithm of KMDLA are proposed in this paper. The key idea of MDLA is as follows. First
MNF transforms data from the original space into a new subspace. In the process
the SNR is used to improve the order of components
and the noise in the image can be effectively reduced by sorting according to the image quality. Second
DLA is performed in the new subspace to obtain the result of feature extraction. KMDLA is the kernel method of MDLA. The main idea of KMNF is as follows. First
the samples are mapped to the high-dimensional feature space by the kernel function in which MNF is conducted. Finally
DLA is performed in the subspace spanned by KMNF
further enhancing the nonlinear discriminant ability of MDLA for the samples. Three sets of hyperspectral remote sensing images were selected as the study area. A detailed comparison of the proposed algorithms and five algorithms
namely
the PCA
MNF
LDA
CCPGE
and DLA algorithms
is provided in this paper. For a more intuitive comparison
experiments were conducted to classify the images of all bands. The support vector machine classifier was used to classify the results of feature extraction. Experimental results demonstrate that both MDLA and KMDLA outperform the five algorithms of comparison. Compared with DLA
the proposed algorithms exhibited respective improvements of 2.06% and 2.74% on the Purdue Campus data
1.91% and 2.45% on the Indian Pines data
and 1.41% and 2.04% on the Salinas data. In terms of efficiency
MDLA and KMDLA consumed less operation time for classification than DLA when the experimental data was small. KMDLA consumed the most operation time when the experimental data was large
whereas MDLA always consumed minimal operation time. The effect of image quality on the performance of different dimensionality reduction methods is discussed based on the Purdue Campus data. Results show that MDLA and KMDLA can still obtain good classification results with the increasing noise in the image. Therefore
the two proposed algorithms can effectively reduce the noise of hyperspectral remote sensing images
improve the classification accuracy
and classify hyperspectral remote sensing images accurately.
高光谱遥感特征提取MDLAKMDLA图像分类
hyperspectral remote sensingfeature extractionMDLAKMDLAimage classification
Bach F R and Jordan M I. 2003. Kernel independent component analysis. Journal of Machine Learning Research, 3(1): 1-48 [DOI: 10.1162/153244303768966085http://dx.doi.org/10.1162/153244303768966085]
Bachmann C M, Ainsworth T L and Fusina R A. 2005. Exploiting manifold geometry in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 43(3): 441-454 [DOI: 10.1109/TGRS.2004.842292http://dx.doi.org/10.1109/TGRS.2004.842292]
Baudat G and Anouar F. 2000. Generalized discriminant analysis using a kernel approach. Neural Computation, 12(10): 2385-2404 [DOI: 10.1162/089976600300014980http://dx.doi.org/10.1162/089976600300014980]
Belkin M and Niyogi P. 2003. Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation, 15(6): 1373-1396 [DOI: 10.1162/089976603321780317http://dx.doi.org/10.1162/089976603321780317]
Bengio Y, Paiement J F, Vincent P, Delalleau O, Roux N L and Ouimet M. 2004. Out-of-sample extensions for LLE, isomap, MDS, eigenmaps, and spectral clustering//Thrun S, Saul L K and Schölkopf B, eds. Advances in Neural Information Processing Systems. Cambridge: MIT Press: 177-184
Du P J, Xia J S, Xue Z H, Tan K, Su H J and Bao R. 2016. Review of hyperspectral remote sensing image classification. Journal of Remote Sensing, 20(2): 236-256
杜培军, 夏俊士, 薛朝辉, 谭琨, 苏红军, 鲍蕊. 2016. 高光谱遥感影像分类研究进展. 遥感学报, 20(2): 236-256 [DOI: 10.11834/jrs.20165022http://dx.doi.org/10.11834/jrs.20165022]
Farrell M D and Mersereau R M. 2005. On the impact of PCA dimension reduction for hyperspectral detection of difficult targets. IEEE Geoscience and Remote Sensing Letters, 2(2): 192-195 [DOI: 10.1109/LGRS.2005.846011http://dx.doi.org/10.1109/LGRS.2005.846011]
Gao L R, Zhao B, Jia X P, Liao W Z and Zhang B. 2017. Optimized kernel minimum noise fraction transformation for hyperspectral image classification. Remote Sensing, 9(6): 548 [DOI: 10.3390/rs9060548http://dx.doi.org/10.3390/rs9060548]
Green A A, Berman M, Switzer P and Craig M D. 1988. A transformation for ordering multispectral data in terms of image quality with implications for noise removal. IEEE Transactions on Geoscience and Remote Sensing, 26(1): 65-74 [DOI: 10.1109/36.3001http://dx.doi.org/10.1109/36.3001]
Guo Y C, Ding G G, Liu L, Han J G and Shao L. 2017. Learning to hash with optimized anchor embedding for scalable retrieval. IEEE Transactions on Image Processing, 26(3): 1344-1354 [DOI: 10.1109/TIP.2017.2652730http://dx.doi.org/10.1109/TIP.2017.2652730]
Jia Y F, Tian Y, Li Y J and Fu P B. 2017. Exponential discriminative locality alignment for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 14(1): 33-37 [DOI: 10.1109/LGRS.2016.2624338http://dx.doi.org/10.1109/LGRS.2016.2624338]
Lin N, Yang W N and Wang B. 2014. Multi-class SVM classification for hyperspectral remote sensing image based on kernel minimum noise fraction transform. Computer Applications and Software, 31(6): 116-119
林娜, 杨武年, 王斌. 2014. 基于核最小噪声分离变换的高光谱遥感影像多类SVM分类. 计算机应用与软件, 31(6): 116-119 [DOI: 10.3969/j.issn.1000-386x.2014.06.032http://dx.doi.org/10.3969/j.issn.1000-386x.2014.06.032]
Liu N, Li W and Du Q. 2018. Unsupervised feature extraction for hyperspectral imagery using collaboration-competition graph. IEEE Journal of Selected Topics in Signal Processing, 12(6): 1491-1503 [DOI: 10.1109/JSTSP.2018.2877474http://dx.doi.org/10.1109/JSTSP.2018.2877474]
Liu Z H and Jin Z. 2011. Enhanced discriminative locality alignment and its kernel extension. Optical Engineering, 50(8): 087002 [DOI: 10.1117/1.3605477http://dx.doi.org/10.1117/1.3605477]
Luo G C, Chen G Y, Tian L, Qin K and Qian S E. 2016. Minimum noise fraction versus principal component analysis as a preprocessing step for hyperspectral imagery denoising. Canadian Journal of Remote Sensing, 42(2): 106-116 [DOI: 10.1080/07038992.2016.1160772http://dx.doi.org/10.1080/07038992.2016.1160772]
Luo R B, Wen Y, Liu X N and Wu Z F. 2018. Feature extraction of hyperspectral images with semi-supervised Sparse graph learning//Proceedings of 2018 Fifth International Workshop on Earth Observation and Remote Sensing Applications (EORSA). Xi’an: IEEE [DOI: 10.1109/EORSA.2018.8598561http://dx.doi.org/10.1109/EORSA.2018.8598561]
Nielsen A A. 2011. Kernel maximum autocorrelation factor and minimum noise fraction transformations. IEEE Transactions on Image Processing, 20(3): 612-624 [DOI: 10.1109/TIP.2010.2076296http://dx.doi.org/10.1109/TIP.2010.2076296]
Roweis S T and Saul L K. 2000. Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500): 2323-2326 [DOI: 10.1126/science.290.5500.2323http://dx.doi.org/10.1126/science.290.5500.2323]
Schölkopf B, Smola A and Müller K R. 1997. Kernel principal component analysis//Proceedings of the 7th International Conference on Artificial Neural Networks. Switzerland: Springer: 583-588 [DOI: 10.1007/BFb0020217http://dx.doi.org/10.1007/BFb0020217]
Shawe-Taylor J and Cristianini N. 2004. Kernel Methods for Pattern Analysis. Cambridge: Cambridge University Press: 115-116
Sun W W and Du Q. 2019. Hyperspectral band selection: a review. IEEE Geoscience and Remote Sensing Magazine, 7(2): 118-139 [DOI: 10.1109/MGRS.2019.2911100http://dx.doi.org/10.1109/MGRS.2019.2911100]
Sun W W, Yang G, Du B, Zhang L F and Zhang L P. 2017. A sparse and low-rank near-isometric linear embedding method for feature extraction in hyperspectral imagery classification. IEEE Transactions on Geoscience and Remote Sensing, 55(7): 4032-4046 [DOI: 10.1109/TGRS.2017.2686842http://dx.doi.org/10.1109/TGRS.2017.2686842]
Tao D P, Liang L Y, Jin L W and Gao Y. 2014. Similar handwritten Chinese character recognition by kernel discriminative locality alignment. Pattern Recognition Letters, 35: 186-194 [DOI: 10.1016/j.patrec.2012.06.014http://dx.doi.org/10.1016/j.patrec.2012.06.014]
Tong Q X, Zhang B and Zheng L F. 2006. Hyperspectral Remote Sensing: the Principle, Technology and Application. Beijing: Higher Education Press
童庆禧, 张兵, 郑兰芬. 2006. 高光谱遥感: 原理、技术与应用. 北京:高等教育出版社
Wang M Y, Wan Y C, Ye Z W, Gao X J and Lai X D. 2018. A band selection method for airborne hyperspectral image based on chaotic binary coded gravitational search algorithm. Neurocomputing, 273: 57-67 [DOI: 10.1016/j.neucom.2017.07.059http://dx.doi.org/10.1016/j.neucom.2017.07.059]
Zhan Y, Hu D, Xing H H and Yu X C. 2017. Hyperspectral band selection based on deep convolutional neural network and distance density. IEEE Geoscience and Remote Sensing Letters, 14(12): 2365-2369 [DOI: 10.1109/LGRS.2017.2765339http://dx.doi.org/10.1109/LGRS.2017.2765339]
Zhang B. 2016. Advancement of hyperspectral image processing and information extraction. Journal of Remote Sensing, 20(5): 1062-1090
张兵. 2016. 高光谱图像处理与信息提取前沿. 遥感学报, 20(5): 1062-1090 [DOI: 10.11834/jrs.20166179http://dx.doi.org/10.11834/jrs.20166179]
Zhang L F, Zhang L P, Tao D C, Huang X and Xia G S. 2013. Nonnegative discriminative manifold learning for hyperspectral data dimension reduction//Proceedings of 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). Gainesville: IEEE: 1-4 [DOI: 10.1109/WHISPERS.2013.8080702http://dx.doi.org/10.1109/WHISPERS.2013.8080702]
Zhang M Y, Ma J J and Gong M G. 2017. Unsupervised hyperspectral band selection by fuzzy clustering with particle swarm optimization. IEEE Geoscience and Remote Sensing Letters, 14(5): 773-777 [DOI: 10.1109/LGRS.2017.2681118http://dx.doi.org/10.1109/LGRS.2017.2681118]
Zhang T H, Tao D C, Li X L and Yang J. 2009. Patch alignment for dimensionality reduction. IEEE Transactions on Knowledge and Data Engineering, 21(9): 1299-1313 [DOI: 10.1109/TKDE.2008.212http://dx.doi.org/10.1109/TKDE.2008.212]
Zhang Z Y and Zha H Y. 2004. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. Journal of Shanghai University (English Edition), 8(4): 406-424 [DOI: 10.1007/s11741-004-0051-1http://dx.doi.org/10.1007/s11741-004-0051-1]
相关作者
相关机构
京公网安备11010802024621