浏览全部资源
扫码关注微信
Published： 07 January 2024 ，
扫 描 看 全 文
何珂，孙伟伟，黄可，陈镔捷，杨刚.2024.基于多特征深度子空间聚类的高光谱影像波段选择.遥感学报，28（1）： 132-141
He K，Sun W W，Huang K，Chen B J and Yang G. 2024. Multi-feature deep subspace clustering for hyperspectral band selection. National Remote Sensing Bulletin， 28（1）：132-141
高光谱影像受到高维波段间强相关性的困扰，导致处理应用的困难。而现有高光谱波段选择方法通常以线性角度考虑波段间关系，未充分考虑多尺度的信息且容易受到噪声的影响，导致所选的波段子集性能不佳。为了克服上述问题，本文提出了基于多特征的深度子空间聚类方法进行高光谱影像波段选择。该方法将自表达层嵌入到卷积自编码器中学习子空间自表达系数，充分考虑了空间信息和光谱信息的交互，用非线性的视角思考了波段间关系。为了提高潜在表征的学习能力，提升自表达系数学习的准确性，本文将注意力模块和多特征提取模块与卷积自编码器相结合，进一步降低了异常值的干扰。本文在3个高光谱遥感影像数据集上，将提出的方法与几种经典主流的方法进行多种对比实验，证明了本文方法能够选择具有代表性的波段子集。
Hyperspectral Images (HSIs) contain abundant spectral information of ground objects through dozens or even hundreds of contiguous narrow bands with a high spatial resolution. However
HSIs are plagued by strong correlation between high-dimensional bands
which increases the difficulty in processing and applications of HSIs. Therefore
dimensionality reduction is one of the important steps of hyperspectral preprocessing. Band selection can effectively preserve the spectral significance of HSIs; thus
it is broadly used for dimensionality reduction. Unfortunately
the existing hyperspectral band selection methods typically consider inter-band relationships in a linear perspective while only partially focusing on multiscale information and demonstrating susceptibility to noise
resulting in poor performance of the subset of bands selected by existing methods. This paper proposes a multifeature deep subspace clustering for HSI band selection to overcome the above problems.
MFDSC embeds the self-expression layer into the autoencoder to learn subspace self-expression coefficients
which considers the interaction of spatial and spectral information and explores the inter-band relationship with a nonlinear perspective. In addition
this paper couples the spatial-spectral attention and multifeature extraction modules with DSC to further reduce the interference of outliers and improve the learning capability of latent representation
thus enhancing the accuracy of self-expression coefficients. MFDSC starts with a spatial–spectral attention module to reweight the HSI to suppress useless information such as noise. Afterward
MFDSC uses convolution kernels of different sizes to extract features at different scales for encoding. Then
MFDSC learns the subspace coefficient matrix through the self-expression layer and reconstructs the original HSI using the decoder. Finally
the subspace coefficient matrix is partitioned using spectral clustering
and the bands closest to the cluster center in each class are calculated. These bands are the final results of band selection.
In this paper
the proposed method is compared with the five state-of-the-art methods in a variety of experiments on three hyperspectral datasets (i.e.
Indian Pines
PaviaU
and YRD datasets). The support vector machine
which adopts radial basis function as kernels
is employed as the classifier. Experimental results demonstrate that the proposed method can attain better performances than the comparison methods. Superior results are obtained when the number of bands reaches a certain number instead of using all bands. In addition
the computational efficiency of MFDSC is acceptable and significantly faster than that of DARecNet
which is a deep learning-based method.
MFDSC considers the interference of noise and outliers on the self-expression performance of subspace clustering. Meanwhile
MFDSC nonlinearly learns the latent representation of data at different scales without deepening the network depth based on multiscale autoencoders. Thus
MFDSC can select a representative subset of bands and reduce the difficulty of subsequent applications.
高光谱遥感降维波段选择多特征深度子空间聚类
hyperspectral remote sensingdimensionality reductionband selectionmulti-featuredeep subspace clustering
Archibald R and Fann G. 2007. Feature selection and classification of hyperspectral images with support vector machines. IEEE Geoscience and Remote Sensing Letters, 4(4): 674-677 [DOI: 10.1109/lgrs.2007.905116http://dx.doi.org/10.1109/lgrs.2007.905116]
Cai Y M, Zeng M, Cai Z H, Liu X B and Zhang Z J. 2021. Graph regularized residual subspace clustering network for hyperspectral image clustering. Information Sciences, 578: 85-101 [DOI: 10.1016/j.ins.2021.07.003http://dx.doi.org/10.1016/j.ins.2021.07.003]
Chen Y, Nasrabadi N M and Tran T D. 2011. Sparse representation for target detection in hyperspectral imagery. IEEE Journal of Selected Topics in Signal Processing, 5(3): 629-640 [DOI: 10.1109/JSTSP.2011.2113170http://dx.doi.org/10.1109/JSTSP.2011.2113170]
Du Q and Yang H. 2008. Similarity-based unsupervised band selection for hyperspectral image analysis. IEEE geoscience and remote sensing letters, 5(4): 564-568.[ DOI: 10.1109/LGRS.2008.2000619]
Elhamifar E and Vidal R. 2013. Sparse subspace clustering: algorithm, theory, and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(11): 2765-2781 [DOI: 10.1109/TPAMI.2013.57http://dx.doi.org/10.1109/TPAMI.2013.57]
Fu J, Liu J, Tian H J, Li Y, Bao Y J, Fang Z W and Lu H Q. 2019. Dual attention network for scene segmentation//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE: 3141-3149 [DOI: 10.1109/CVPR.2019.00326http://dx.doi.org/10.1109/CVPR.2019.00326]
Geng X R, Sun K, Ji L Y and Zhao Y C. 2014. A fast volume-gradient-based band selection method for hyperspectral image. IEEE Transactions on Geoscience and Remote Sensing, 52(11): 7111-7119. [DOI: 10.1109/TGRS.2014.2307880http://dx.doi.org/10.1109/TGRS.2014.2307880]
He K, Sun W W, Yang G, Meng X C, Ren K, Peng J T and Du Q. 2022. A dual global-local attention network for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5527613 [DOI: 10.1109/TGRS.2022.3169018http://dx.doi.org/10.1109/TGRS.2022.3169018]
Jia S, Tang G H, Zhu J S and Li Q Q. 2016. A novel ranking-based clustering approach for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 54(1): 88-102 [DOI: 10.1109/tgrs.2015.2450759http://dx.doi.org/10.1109/tgrs.2015.2450759]
Jiao L L, Sun W W, Yang G, Ren G B and Liu Y N. 2019. A hierarchical classification framework of satellite multispectral/hyperspectral images for mapping coastal wetlands. Remote Sensing, 11(19): 2238 [DOI: 10.3390/rs11192238http://dx.doi.org/10.3390/rs11192238]
Roy S K, Das S, Song T C and Chanda B. 2021. DARecNet-BS: unsupervised dual-attention reconstruction network for hyperspectral band selection. IEEE Geoscience and Remote Sensing Letters, 18(12): 2152-2156 [DOI: 10.1109/lgrs.2020.3013235http://dx.doi.org/10.1109/lgrs.2020.3013235]
Su H J. 2022. Dimensionality reduction for hyperspectral remote sensing: advances, challenges, and prospects. National Remote Sensing Bulletin, 26(8): 1504-1529
苏红军. 2022. 高光谱遥感影像降维: 进展、挑战与展望. 遥感学报, 26(8): 1504-1529 [DOI: 10.11834/jrs.20210354http://dx.doi.org/10.11834/jrs.20210354]
Su H J, Sheng Y H and Du P J. 2008. A new band selection algorithm for hyperspectral data based on fractal dimension. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 37(B7): 279-284
Sun W W, and Du Q. 2018. Graph-regularized fast and robust principal component analysis for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 56(6): 3185-3195. [DOI: 10.1109/TGRS.2018.2794443http://dx.doi.org/10.1109/TGRS.2018.2794443]
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, Peng J T, Yang G and Du Q. 2020. Fast and latent low-rank subspace clustering for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 58(6): 3906-3915 [DOI: 10.1109/TGRS.2019.2959342http://dx.doi.org/10.1109/TGRS.2019.2959342]
Sun W W, Tian L, Xu Y, Zhang D, Du Q. 2017. Fast and robust self-representation method for hyperspectral band selection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(11): 5087-5098. [DOI: 10.1109/JSTARS.2017.2737400http://dx.doi.org/10.1109/JSTARS.2017.2737400]
Sun W W, Yang G, Peng J T and Meng X C. 2022. Robust multi-feature spectral clustering for hyperspectral band selection. National Remote Sensing Bulletin, 26(2): 397-405
孙伟伟, 杨刚, 彭江涛, 孟祥超. 2022. 鲁棒多特征谱聚类的高光谱影像波段选择. 遥感学报, 26(2): 397-405 [DOI: 10.11834/jrs.20209165http://dx.doi.org/10.11834/jrs.20209165]
Sun W W, Yang G, Peng J T, Meng X C, He K, Li W, Li H C and Du Q. 2022. A multiscale spectral features graph fusion method for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5513712 [DOI:10.1109/TGRS.2021.3102246http://dx.doi.org/10.1109/TGRS.2021.3102246]
Sun W W, Zhang L P, Du B, Li W Y and Mark Lai Y. 2015. Band selection using improved sparse subspace clustering for hyperspectral imagery classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2784-2797 [DOI: 10.1109/jstars.2015.2417156http://dx.doi.org/10.1109/jstars.2015.2417156]
Sun W W, Zhang L P, Zhang L F and Lai Y M. 2016. A dissimilarity-weighted sparse self-representation method for band selection in hyperspectral imagery classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(9): 4374-4388 [DOI: 10.1109/JSTARS.2016.2539981http://dx.doi.org/10.1109/JSTARS.2016.2539981]
Wang W W, Li X P, Feng X C and Wang S Q. 2015. A survey on sparse subspace clustering. Acta Automatica Sinica, 41(8): 1373-1384
王卫卫, 李小平, 冯象初, 王斯琪. 2015. 稀疏子空间聚类综述. 自动化学报, 41(8): 1373-1384 [DOI: 10.16383/j.aas.2015.c140891http://dx.doi.org/10.16383/j.aas.2015.c140891]
Yuan Y, Lin J and Wang Q. 2015. Dual-clustering-based hyperspectral band selection by contextual analysis. IEEE Transactions on Geoscience and Remote Sensing, 54(3): 1431-1445. [DOI: 10.1109/TGRS.2015.2480866http://dx.doi.org/10.1109/TGRS.2015.2480866]
Zeng M, Cai Y M, Cai Z H, Liu X B, Hu P and Ku J H. 2019. Unsupervised hyperspectral image band selection based on deep subspace clustering. IEEE Geoscience and Remote Sensing Letters, 16(12): 1889-1893 [DOI: 10.1109/lgrs.2019.2912170http://dx.doi.org/10.1109/lgrs.2019.2912170]
Zhu D H, Du B and Zhang L P. 2020. Band selection-based collaborative representation for anomaly detection in hyperspectral images. Journal of Remote Sensing (Chinese), 24(4): 427-438
朱德辉, 杜博, 张良培. 2020. 波段选择协同表达高光谱异常探测算法. 遥感学报, 24(4): 427-438 [DOI: 10.11834/jrs.20209187http://dx.doi.org/10.11834/jrs.20209187]
相关文章
相关作者
相关机构
京公网安备11010802024621