基于稀疏表示和光谱自回归的多光谱和高光谱图像融合
Multispectral and Hyperspectral Image Fusion Based on Sparse Representation and Spectral Autoregression
DOI: 10.12677/mos.2024.133292, PDF,   
作者: 钱金明：上海理工大学光电信息与计算机工程学院，上海
关键词: 图像融合；高光谱图像；稀疏表示；光谱自回归；Image Fusion； Hyperspectral Image； Sparse Representation； Spectral Autoregression
摘要: 现有的高光谱图像融合算法采用将空间维度与光谱维度进行分开融合重建的方式，而高光谱图像光谱维度存在大量的光谱信息，这些像素信息比空间上的像素更加接近目标像素，对于空间维度的重建非常关键。因此，本文提出一种将光谱像素用于对空间维度进行空间信息修复的融合方法，称作基于稀疏表示和光谱自回归的多光谱和高光谱图像融合。该方法通过将光谱维度上的像素，通过自回归模型将其用于空间维度的信息修复，自回归模型由低分辨率的高光谱图像中学习得到，该模型自然保持了光谱间的关联性，通过在公开数据集上的验证了提出模型的有效性。
Abstract: Existing hyperspectral image fusion algorithms use separate fusion reconstruction of spatial and spectral dimensions, whereas there is a large amount of spectral information in the spectral dimension of hyperspectral images, and the information of these pixels is much closer to the target pixels than spatially similar pixels, which is very critical for the reconstruction of the spatial dimension. Therefore, in this paper, we propose a method to use spectral pixels for spatial information restoration on the spatial dimension, called multispectral and hyperspectral image fusion based on sparse representation and spectral autoregression. The method works by taking the pixels on the spectral dimension and using them for information restoration on the spatial dimension through an autoregressive model, the autoregressive model is learned from low-resolution hyperspectral images, which naturally maintains the correlation between the spectra, and the validity of the proposed model is verified by the validation on the publicly available dataset.
文章引用：钱金明. 基于稀疏表示和光谱自回归的多光谱和高光谱图像融合[J]. 建模与仿真, 2024, 13(3): 3196-3211. https://doi.org/10.12677/mos.2024.133292

参考文献

[1] Bioucas-Dias, J.M., Plaza, A., Camps-Valls, G., et al. (2013) Hyperspectral Remote Sensing Data Analysis and Future Challenges. IEEE Geoscience and Remote Sensing Magazine, 1, 6-36. [Google Scholar] [CrossRef] 
[2] Akhtar, N. and Mian, A. (2018) Nonparametric Coupled Bayesian Dictionary and Classifier Learning for Hyperspectral Classification. IEEE Transactions on Neural Networks and Learning Systems, 29, 4038-4050. [Google Scholar] [CrossRef] 
[3] Zhang, Y., Du, B., Zhang, L. and Liu, T. (2017) Joint Sparse Representation and Multitask Learning for Hyperspectral Target Detection. IEEE Transactions on Geoscience & Remote Sensing, 55, 894-906. [Google Scholar] [CrossRef] 
[4] Deng, L.J., Feng, M. and Tai, X.C. (2019) The Fusion of Panchromatic and Multispectral Remote Sensing Images via Tensor-Based Sparse Modeling and Hyper-Laplacian Prior. Information Fusion, 52, 76-89. [Google Scholar] [CrossRef] 
[5] Ma, J., Yu, W., Chen, C., et al. (2020) Pan-GAN: An Unsupervised Pan-Sharpening Method for Remote Sensing Image Fusion. Information Fusion, 62, 110-120. [Google Scholar] [CrossRef] 
[6] Meng, X., Shen, H., Yuan, Q., et al. (2019) Pansharpening for Cloud-Contaminated Very High-Resolution Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 57, 2840-2854. [Google Scholar] [CrossRef] 
[7] Chen, Z., Pu, H., Wang, B. and Jiang, G.M. (2014) Fusion of Hyperspectral and Multispectral Images: A Novel Framework Based on Generalization of Pan-Sharpening Methods. IEEE Geoscience and Remote Sensing Letters, 11, 1418-1422. [Google Scholar] [CrossRef] 
[8] Selva, M., Aiazzi, B., Butera, F., Chiarantini, L. and Baronti, S. (2015) Hyper-Sharpening: A First Approach on SIM-GA Data. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 8, 3008-3024. [Google Scholar] [CrossRef] 
[9] Akhtar, N., Shafait, F. and Mian, A. (2014) Sparse Spatio-Spectral Representation for Hyperspectral Image Super-Resolution. In: Fleet, D., Pajdla, T., Schiele, B. and Tuytelaars, T., Eds., Computer Vision—ECCV 2014, Springer, Cham, 63-78. [Google Scholar] [CrossRef] 
[10] Huang, B., Song, H., Cui, H., et al. (2013) Spatial and Spectral Image Fusion Using Sparse Matrix Factorization. IEEE Transactions on Geoscience & Remote Sensing, 52, 1693-1704. [Google Scholar] [CrossRef] 
[11] Dong, W., Fu, F., Shi, G., et al. (2016) Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse Representation. IEEE Transactions on Image Processing, 25, 2337-2352. [Google Scholar] [CrossRef] 
[12] Liu, J., Wu, Z., Xiao, L., et al. (2020) A Truncated Matrix Decomposition for Hyperspectral Image Super-Resolution. IEEE Transactions on Image Processing, 29, 8028-8042. [Google Scholar] [CrossRef] 
[13] Wei, Q., Bioucas-Dias, J., Dobigeon, N., et al. (2015) Hyperspectral and Multispectral Image Fusion Based on a Sparse Representation. IEEE Transactions on Geoscience & Remote Sensing, 53, 3658-3668. [Google Scholar] [CrossRef] 
[14] Yokoya, N., Miyamura, N. and Iwasaki, A. (2010) Detection and Correction of Spectral and Spatial Misregistrations for Hyperspectral Data Using Phase Correlation Method. 2010 IEEE International Geoscience and Remote Sensing Symposium, Honolulu, 25-30 July 2010, 1003-1006. [Google Scholar] [CrossRef] 
[15] Kawakami, R., Matsushita, Y., Wright, J., et al. (2011) High-Resolution Hyperspectral Imaging via Matrix Factorization. CVPR 2011, Colorado Springs, 20-25 June 2011, 2329-2336. [Google Scholar] [CrossRef] 
[16] Zhou, Y., Feng, L., Hou, C. and Kung, S.Y. (2017) Hyperspectral and Multispectral Image Fusion Based on Local Low Rank and Coupled Spectral Unmixing. IEEE Transactions on Geoscience & Remote Sensing, 55, 5997-6009. [Google Scholar] [CrossRef] 
[17] Veganzones, M.A., Simoes, M., Licciardi, G., et al. (2015) Hyperspectral Super-Resolution of Locally Low Rank Images from Complementary Multisource Data. IEEE Transactions on Image Processing, 25, 274-288. [Google Scholar] [CrossRef] 
[18] Dian, R. and Li, S. (2019) Hyperspectral Image Super-Resolution via Subspace-Based Low Tensor Multi-Rank Regularization. IEEE Transactions on Image Processing, 28, 5135-5146. [Google Scholar] [CrossRef] 
[19] Dian, R., Li, S. and Fang, L. (2019) Learning a Low Tensor-Train Rank Representation for Hyperspectral Image Super-Resolution. IEEE Transactions on Neural Networks and Learning Systems, 30, 2672-2683. [Google Scholar] [CrossRef] 
[20] Li, S., Dian, R., Fang, L., et al. (2018) Fusing Hyperspectral and Multispectral Imagesvia Coupled Sparse Tensor Factorization. IEEE Transactions on Image Processing, 27, 4118-4130. [Google Scholar] [CrossRef] 
[21] Xie, Q., Zhou, M., Zhao, Q., et al. (2019) Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 1585-1594. [Google Scholar] [CrossRef] 
[22] Wang, W., Fu, X., Zeng, W., et al. (2021) Enhanced Deep Blind Hyperspectral Image Fusion. IEEE Transactions on Neural Networks and Learning Systems, 34, 1513-1523. [Google Scholar] [CrossRef] 
[23] Achanta, R., Shaji, A., Smith, K., et al. (2012) SLIC Superpixels Compared to State-Of-The-Art Superpixel Methods. IEEE Transactions on Pattern Analysis & Machine Intelligence, 34, 2274-2282. [Google Scholar] [CrossRef] 
[24] Bioucas-Dias, J., Simoes, M., Almeida, L.B. and Chanussot, J. (2015) A Convex Formulation for Hyperspectral Image Superresolution via Subspace-Based Regularization. IEEE Transactions on Geoscience and Remote Sensing, 53, 3373-3388. [Google Scholar] [CrossRef] 
[25] Xu, T., Huang, T.Z., Deng, L.J. and Yokoya, N. (2022) An Iterative Regularization Method Based on Tensor Subspace Representation for Hyperspectral Image Super-Resolution. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-16. [Google Scholar] [CrossRef] 

为你推荐