Hyperspectral Images Super-Resolution via Learning High-Order Coupled Tensor Ring Representation

被引:103
作者
Xu, Yang [1 ,2 ,3 ]
Wu, Zebin [1 ,2 ,3 ]
Chanussot, Jocelyn [4 ]
Wei, Zhihui [1 ,2 ,3 ]
机构
[1] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Peoples R China
[2] Nanjing Univ Sci & Technol, Minist Educ, Key Lab Intelligent Percept & Syst High Dimens In, Nanjing 210094, Peoples R China
[3] Nanjing Univ Sci & Technol, Jiangsu Key Lab Image & Video Understanding Socia, Nanjing 210094, Peoples R China
[4] Univ Grenoble Alpes, INRIA, CNRS, Grenoble INP,LJK, F-38000 Grenoble, France
基金
中国国家自然科学基金; 中国博士后科学基金;
关键词
Tensors; Sparse matrices; Hyperspectral imaging; Spatial resolution; Fuses; Hyperspectral image (HSI); multiscale; multispectral image (MSI); super-resolution; tensor ring (TR); FUSION; FACTORIZATION; REGRESSION;
D O I
10.1109/TNNLS.2019.2957527
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Hyperspectral image (HSI) super-resolution is a hot topic in remote sensing and computer vision. Recently, tensor analysis has been proven to be an efficient technology for HSI image processing. However, the existing tensor-based methods of HSI super-resolution are not able to capture the high-order correlations in HSI. In this article, we propose to learn a high-order coupled tensor ring (TR) representation for HSI super-resolution. The proposed method first tensorizes the HSI to be estimated into a high-order tensor in which multiscale spatial structures and the original spectral structure are represented. Then, a coupled TR representation model is proposed to fuse the low-resolution HSI (LR-HSI) and high-resolution multispectral image (HR-MSI). In the proposed model, some latent core tensors in TR of the LR-HSI and the HR-MSI are shared, and we use the relationship between the spectral core tensors to reconstruct the HSI. In addition, the graph-Laplacian regularization is introduced to the spectral core tensors to preserve the spectral information. To enhance the robustness of the proposed model, Frobenius norm regularizations are introduced to the other core tensors. Experimental results on both synthetic and real data sets show that the proposed method achieves the state-of-the-art super-resolution performance.
引用
收藏
页码:4747 / 4760
页数:14
相关论文
共 50 条
  • [41] Hyperspectral Image Super-Resolution Method Based on Spectral Smoothing Prior and Tensor Tubal Row-Sparse Representation
    Sun, Le
    Cheng, Qihao
    Chen, Zhiguo
    REMOTE SENSING, 2022, 14 (09)
  • [42] FuBay: An Integrated Fusion Framework for Hyperspectral Super-Resolution Based on Bayesian Tensor Ring
    Wang, Yinjian
    Li, Wei
    Liu, Na
    Gui, Yuanyuan
    Tao, Ran
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (10) : 14712 - 14726
  • [43] A super-resolution reconstruction algorithm for hyperspectral images
    Zhang, Hongyan
    Zhang, Liangpei
    Shen, Huanfeng
    SIGNAL PROCESSING, 2012, 92 (09) : 2082 - 2096
  • [44] Hyperspectral imagery super-resolution by sparse representation and spectral regularization
    Zhao, Yongqiang
    Yang, Jinxiang
    Zhang, Qingyong
    Song, Lin
    Cheng, Yongmei
    Pan, Quan
    EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2011,
  • [45] HYPERSPECTRAL IMAGES SUPER-RESOLUTION ALGORITHMS BASED ON SPECTRAL SUBSPACE SPARSE TENSOR FACTORIZATION
    Sun, Shasha
    Bao, Wenxing
    Guo, Hao
    Qu, Kewen
    Feng, Wei
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 7455 - 7458
  • [46] Hyperspectral Image Super-Resolution via Intrafusion Network
    Hu, Jing
    Jia, Xiuping
    Li, Yunsong
    He, Gang
    Zhao, Minghua
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (10): : 7459 - 7471
  • [47] Bayesian Nonlocal Patch Tensor Factorization for Hyperspectral Image Super-Resolution
    Ye, Fei
    Wu, Zebin
    Jia, Xiuping
    Chanussot, Jocelyn
    Xu, Yang
    Wei, Zhihui
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 5877 - 5892
  • [48] HYPERSPECTRAL SUPER-RESOLUTION: COMBINING LOW RANK TENSOR AND MATRIX STRUCTURE
    Kanatsoulis, Charilaos I.
    Fu, Xiao
    Sidiropoulos, Nicholas D.
    Ma, Wing-Kin
    2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 3318 - 3322
  • [49] Smooth Coupled Tucker Decomposition for Hyperspectral Image Super-Resolution
    Bu, Yuanyang
    Zhao, Yongqiang
    Xue, Jize
    Chan, Jonathan Cheung-Wai
    PATTERN RECOGNITION AND COMPUTER VISION,, PT III, 2021, 13021 : 238 - 248
  • [50] Multiple Frame Splicing and Degradation Learning for Hyperspectral Imagery Super-Resolution
    Deng, Chenwei
    Luo, Xingshi
    Wang, Wenzheng
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 8389 - 8401