Hyperspectral (HS) imaging has shown its superiority in many real applications. However, it is usually difficult to obtain high-resolution (HR) HS images through existing imaging techniques due to the hardware limitations. To improve the spatial resolution of HS images, this article proposes an effective HS-multispectral (HS-MS) image fusion method by combining the ideas of nonlocal low-rank tensor modeling and spectral unmixing. To be more precise, instead of unfolding the HS image into a matrix as done in the literature, we directly represent it as a tensor, then a designed nonlocal Tucker decomposition is used to model its underlying spatial-spectral correlation and the spatial self-similarity. The MS image serves mainly as a data constraint to maintain spatial consistency. To further reduce the spectral distortions in spatial enhancement, endmembers, and abundances from the spectral are used for spectral regularization. An efficient algorithm based on the alternating direction method of multipliers (ADMM) is developed to solve the resulting model. Extensive experiments on four HS image data sets demonstrate the superiority of the proposed method over several state-of-the-art HS-MS image fusion methods.
Wang, K, Wang, Y, Zhao, X, Chan, JC-W, Xu, Z & Meng, D 2020, 'Hyperspectral and Multispectral Image Fusion via Nonlocal Low-Rank Tensor Decomposition and Spectral Unmixing', IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 11, 9070159, pp. 7654-7671. https://doi.org/10.1109/TGRS.2020.2983063
Wang, K., Wang, Y., Zhao, X., Chan, J. C.-W., Xu, Z., & Meng, D. (2020). Hyperspectral and Multispectral Image Fusion via Nonlocal Low-Rank Tensor Decomposition and Spectral Unmixing. IEEE Transactions on Geoscience and Remote Sensing, 58(11), 7654-7671. Article 9070159. https://doi.org/10.1109/TGRS.2020.2983063
@article{0ecc0cac1e604209b1db7bf8293cd417,
title = "Hyperspectral and Multispectral Image Fusion via Nonlocal Low-Rank Tensor Decomposition and Spectral Unmixing",
abstract = "Hyperspectral (HS) imaging has shown its superiority in many real applications. However, it is usually difficult to obtain high-resolution (HR) HS images through existing imaging techniques due to the hardware limitations. To improve the spatial resolution of HS images, this article proposes an effective HS-multispectral (HS-MS) image fusion method by combining the ideas of nonlocal low-rank tensor modeling and spectral unmixing. To be more precise, instead of unfolding the HS image into a matrix as done in the literature, we directly represent it as a tensor, then a designed nonlocal Tucker decomposition is used to model its underlying spatial-spectral correlation and the spatial self-similarity. The MS image serves mainly as a data constraint to maintain spatial consistency. To further reduce the spectral distortions in spatial enhancement, endmembers, and abundances from the spectral are used for spectral regularization. An efficient algorithm based on the alternating direction method of multipliers (ADMM) is developed to solve the resulting model. Extensive experiments on four HS image data sets demonstrate the superiority of the proposed method over several state-of-the-art HS-MS image fusion methods. ",
author = "Kaidong Wang and Yao Wang and Xile Zhao and Chan, {Jonathan Cheung-Wai} and Zongben Xu and Deyu Meng",
note = "Funding Information: Manuscript received May 19, 2019; revised October 16, 2019 and January 30, 2020; accepted February 28, 2020. Date of publication April 17, 2020; date of current version October 27, 2020. This work was supported in part by the National Key Research and Development Program of China under Grant 2018YFB1402600, in part the National Natural Science Foundation of China under Grant 11971374, Grant 11501440, Grant 61603292, Grant 91846110, and Grant 61876203, in part by the Fundamental Research Funds for the Central Universities under Grant xjj2018085, and in part by the MoE-CMCC Artifical Intelligence Project under Grant MCM20190701. (Corresponding author: Yao Wang.) Kaidong Wang is with the School of Mathematics and Statistics, Xi{\textquoteright}an Jiaotong University, Xi{\textquoteright}an 710049, China, and also with the Center for Intelligent Decision-making and Machine Learning, School of Management, Xi{\textquoteright}an Jiaotong University, Xi{\textquoteright}an 710049, China. Publisher Copyright: {\textcopyright} 1980-2012 IEEE. Copyright: Copyright 2022 Elsevier B.V., All rights reserved.",
year = "2020",
month = nov,
doi = "10.1109/TGRS.2020.2983063",
language = "English",
volume = "58",
pages = "7654--7671",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",
}