计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (8): 240-250.doi: 10.11896/jsjkx.240600026

• 计算机图形学&多媒体 • 上一篇    下一篇

基于张量环子空间平滑与图正则的高光谱图像超分辨率方法研究

杨飞霞1, 李正1, 马飞2   

  1. 1 辽宁工程技术大学电气与控制工程学院 辽宁 葫芦岛 125105
    2 辽宁工程技术大学电子与信息工程学院 辽宁 葫芦岛 125105
  • 收稿日期:2024-06-03 修回日期:2024-10-09 出版日期:2025-08-15 发布日期:2025-08-08
  • 通讯作者: 李正(1595587774@qq.com)
  • 作者简介:(yangfx091011@gmail.com)
  • 基金资助:
    辽宁省自然科学基金(2023-MS-314);辽宁省教育厅基本科研创新发展项目(LJ242410147006)

Research on Hyperspectral Image Super-resolution Methods Based on Tensor Ring SubspaceSmoothing and Graph Regularization

YANG Feixia1, LI Zheng1, MA Fei2   

  1. 1 School of Electrical and Control Engineering,Liaoning Technical University,Huludao,Liaoning 125105,China
    2 School of Electronic and Information Engineering,Liaoning Technical University,Huludao,Liaoning 125105,China
  • Received:2024-06-03 Revised:2024-10-09 Online:2025-08-15 Published:2025-08-08
  • About author:YANG Feixia,born in 1979,Ph.D,associate professor.Her main research interests include digital image proces-sing,remote sensing imaging and pattern recognition.
    LI Zheng,born in 1998,postgraduate.His main research interests include hyperspectral image processing,convex optimization and machine learning.
  • Supported by:
    Natural Science Foundation of Liaoning Province,China(2023-MS-314) and Basic Research and Innovation Development Project of Education Department of Liaoning Province,China(LJ242410147006).

PDF (PC)

15

摘要： 针对现有经典的矩阵分解模型会导致三维数据结构信息丢失,特别是受到噪声污染时重构图像质量严重下降等问题,提出了一种子空间平滑正则化与图正则相结合的高光谱与多光谱图像融合的方法,在保持立方体结构特征的同时利用流形结构与局部平滑特性来实现高光谱图像超分辨率的重建。首先,利用空间子空间与光谱子空间的局部自相似性,通过张量环因子构建空间图和光谱图来挖掘空间光谱流形结构,以提升重建图像质量;其次,引入子空间平滑正则化用于促进目标图像子空间的分段平滑;最后,设计一种高效的近端交替最小化算法对所提出的算法进行求解。在3个常用的实验数据集上进行的实验表明,所提出的模型不仅能改善空间细节和结构,在一定程度上还能抑制噪声。

关键词: 高光谱图像, 高光谱与多光谱图像融合, 张量环分解, 图正则, 子空间平滑正则化

Abstract: Regarding existing classical matrix decomposition models,they may lead to the loss of three-dimensional data structure information,especially when affected by noise pollution,resulting in a significant decrease in the quality of reconstructed images,this paper proposes a method for hyperspectral and multispectral fusion that combines subspace smoothing with graph regularization.This approach aims to achieve hyperspectral image super-resolution reconstruction by utilizing manifold structures and local smoothing characteristics,while preserving cube structure features.Firstly,the local self-similarity between spatial subspace and spectral subspace is used to construct spatial and spectral maps by tensor ring factors to mine spatial spectral manifold structure to improve the quality of reconstructed images.Secondly,the subspace smoothing regularization is introduced to promote the segmentation smoothing of the subspace of the target image.Finally,an efficient proximal alternating minimization algorithm is designed to solve the proposed model.Experiments on three commonly used experimental data sets show that the proposed model can improve the spatial details and structure while suppressing the noise to a certain extent.

Key words: Hyperspectral imaging, Hyperspectral and multispectral image fusion, Tensor ring decomposition, Graph regularization, Subspace smoothing regularization

中图分类号: 

  • TP751
[1]JIANG B,YE J,ZHANG L H,et al.Hyperspectral image restoration Model based on double smoothing function rank approximation and group sparsity [J].Computer Science,2024,51(5):151-161.
[2]VIVONE G.Multispectral and hyperspectral image fusion in remote sensing:A survey [J].Information Fusion,2023,89:405-417.
[3]WANG J,LU T,HUANG X,et al.Pan-sharpening via condi-tional invertible neural network [J].Information Fusion,2024,101:10198.
[4]LIU X,HOU J,CONG X,et al.Rethinking Pan-Sharpening via Spectral-Band Modulation [J].IEEE Transactions on Geo-science and Remote Sensing,2024,62:1-16.
[5]WANG Z,NG M K,MICHALSKI J,et al.A Self-SupervisedDeep Denoiser for Hyperspectral and Multispectral Image Fusion [J].IEEE Trans Geosci Remote Sens,2023,61:1-14.
[6]MA Q,JIANG J,LIU X,et al.Reciprocal transformer for hyperspectral and multispectral image fusion [J].Information Fusion,2024,104:102148.
[7]CHEN Y,HUANG T Z,HE W,et al.Hyperspectral Image Denoising Using Factor Group Sparsity-Regularized Nonconvex Low-Rank Approximation [J].IEEE Transactions on Geos-cience and Remote Sensing,2022,60:1-16.
[8]WANG S,HUANG T Z,ZHAO X L,et al.Reweighted sparse unmixing for hyperspectral images with noise level estimation [J].Journal of Computational and Applied Mathematics,2023,421:114843.
[9]RAHICHE A,CHERIET M.Blind Decomposition of Multispectral Document Images Using Orthogonal Nonnegative Matrix Factorization [J].IEEE Transactions on Image Processing,2021,30(1):5997-6012.
[10]KANATSOULIS C I,FU X,SIDIROPOULOS N D,et al.Hyperspectral Super-Resolution:A Coupled Tensor Factorization Approach [J].Sport Psychologist,2018,66(24):6503-6517.
[11]LI S,DIAN R,FANG L,et al.Fusing Hyperspectral and Multispectral Images via Coupled Sparse Tensor Factorization [J].IEEE Transactions on Image Processing,2018,27(8):4118-4130.
[12]LIU H,JIANG W,ZHA Y,et al.Coupled Tensor Block Term Decomposition with Superpixel-Based Graph Laplacian Regularization for Hyperspectral Super-Resolution [J].Remote sensing,2022,14(18):4520.
[13]DIAN R,LI S,FANG L.Learning a low tensor-train rank representation for hyperspectral image super-resolution [J].IEEE Transactions on Neural Networks and Learning Systems,2019,30(9):2672-2683.
[14]ZHAO Q,ZHOU G,XIE S,et al.Tensor ring decomposition[J].arXiv:1606.05535,2016.
[15]JIN D,LIU J,YANG J,et al.High-Order Coupled Fully Connected Tensor Network Decomposition for Hyperspectral Image Super-Resolution [J].IEEE Geoscience and Remote Sensing Letters,2022,19:1-5.
[16]HE W,CHEN Y,YOKOYA N,et al.Hyperspectral super-resolution via coupled tensor ring factorization [J].Pattern Recognition,2022,122:108280.
[17]XU H,QIN M,CHEN S,et al.Hyperspectral-multispectral image fusion via tensor ring and subspace decompositions [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2021,14:8823-8837.
[18]XU Y,WU Z,CHANUSSOT J,et al.Hyperspectral Images Super-Resolution via Learning High-Order Coupled Tensor Ring Representation [J].IEEE Transactions on Neural Networks and Learning Systems,2020,31(11):4747-4760.
[19]CHEN Y,ZENG J,HE W,et al.Hyperspectral and Multispectral Image Fusion Using Factor Smoothed Tensor Ring Decomposition [J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-17.
[20]CANDES E J,WAKIN M B,BOYD S P.Enhancing sparsity by reweighted L1 minimization [J].Journal of Fourier Analysis and Applications,2008,14:877-905.
[21]ZHENG Y B,HUANG T Z,ZHAO X L,et al.Double-Factor-Regularized Low-Rank Tensor Factorization for Mixed Noise Removal in Hyperspectral Image [J].IEEE Transactions on Geo-science and Remote Sensing,2020,58(12):8450-8464.
[22]WEI Q,BIOUCAS-DIAS J M,DOBIGEON N,et al.Multiband Image Fusion Based on Spectral Unmixing [J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(12):3658-3668.
[23]WEI Q,BIOUCAS-DIAS J,DOBIGEON N,et al.Hyperspectral and multispectral image fusion based on a sparse representation [J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(7):3658-3668.
[24]SUN S,BAO W,QU K,et al.Hyperspectral Image Super-Resolution Algorithm Based on Graph Regular Tensor Ring Decomposition [J].Remote Sensing,2023,15(20):4983.
[25]XU T,HUANG T Z,DENG L J,et al.Hyperspectral image superresolution using unidirectional total variation with tucker decomposition [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,13:4381-4398.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发