| 929 | 0 | 52 |
| 下载次数 | 被引频次 | 阅读次数 |
高光谱与多光谱图像融合作为提升遥感图像空间分辨率的关键技术，已成为多源遥感图像融合领域的研究热题。首先，简要阐述了多源遥感图像融合的概念。然后，从融合层次、结构和方法 3个方面系统综述了高光谱与多光谱图像融合的进展：将融合层次归纳为像素级、特征级和决策级3类；将融合结构概括为串联型、并联型和混合型3类；将融合方法详细划分为基于全色锐化和基于监督学习等多类，并分析了传统方法、深度学习及其二者结合的融合方法的区别与联系。最后，讨论了高光谱与多光谱图像融合技术在农业监测和气候变化研究等领域的应用，总结了其在多源信息挖掘和特定场景个性化需求等所面临的问题与挑战，给出针对性的改进方案，并对未来发展进行了展望。
Abstract：Hyperspectral and multispectral image fusion(HS-MS fusion), as a crucial technique for enhancing the spatial resolution of remote sensing(RS) images, has emerged as a focal point in multi-source remote sensing image fusion(MSRS fusion) research. Firstly, the concept of MSRS fusion is introduced. Secondly, the recent advances in HS-MS fusion from the perspectives of fusion levels, architectures, and methodologies are comprehensively reviewed. The fusion levels are classified into three categories including pixel-level, feature-level and decision-level; the fusion structures are summarized into three types containing serial, parallel and hybrid; the fusion methods are comprehensively categorized into multiple categories such as pan-sharpening-based and supervised learning-based methods, and the differences and connections between traditional methods, deep learning methods, and their combined fusion methods are analyzed. Finally, the applications of HS-MS fusion in agricultural monitoring and climate change research are discussed, the problems and challenges faced in multi-source information mining and scenario-specific personalized requirements are summarized, and the targeted improvement solutions are provided. Moreover, prospects for future development are outlined.
[1]SAIDI S,IDBRAIM S,KARMOUDE Y,et al.Deep-learning for change detection using multi-modal fusion of remote sensing images:a review[J].Remote Sensing,2024,16(20):3 852.
[2]TIAN X,ZHANG W,CHEN Y R,et al.Hyperfusion:a computational approach for hyperspectral,multispectral,and panchromatic image fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:5 518216.
[3]QU J H,LEI J,LI Y S,et al.Structure tensor-based algorithm for hyperspectral and panchromatic images fusion[J].Remote Sensing,2018,10(3):373.
[4]DENG S Q,DENG L J,WU X,et al.PSRT:pyramid shuffle-and-reshuffle transformer for multispectral and hyperspectral image fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2023,61:5503715.
[5]MANGOLINI M.Apport de la fusion d'images satellitaires multicapteurs au niveau pixel en télédétection et photo-interprétation[D].Nice:Universitéde Nice Sophia-Antipolis,1994.
[6]DOGRA A,GOYAL B,AGRAWAL S.From multi-scale decomposition to non-multi-scale decomposition methods:a comprehensive survey of image fusion techniques and its applications[J].IEEE Access,2017,5:16040-16067.
[7]LIU J J,SHEN D B,WU Z B,et al.Patch-aware deep hyperspectral and multispectral image fusion by unfolding subspace-based optimization model[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:1024-103 8.
[8]ZHU C Y,ZHANG T H,WU Q,et al.An implicit transformer-based fusion method for hyperspectral and multispectral remote sensing image[J].International Journal of Applied Earth Observation and Geoinformation,2024,131:103 955.
[9]ZHENG Y X,LI J J,LI Y S,et al.Edge-conditioned feature transform network for hyperspectral and multispectral image fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:5513315.
[10]FAROOQUE G,XIAO L,SARGANO A B,et al.A dual attention driven multiscale-multilevel feature fusion approach for hyperspectral image classification[J].International Journal of Remote Sensing,2023,44(4):1151-1178.
[11]SUN L,ZHOU J X,YE Q L,et al.MDC-FusFormer:multiscale deep cross-fusion transformer network for hyperspectral and multispectral image fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2024,62:5528914.
[12]LV G H,XU Y L,GAO Y B,et al.CGNet:classification-guided multi-task interactive network for hyperspectral and multispectral image fusion[C]//2025 IEEE International Conference on Acoustics,Speech and Signal Processing,Hyderabad,India,April 6-11,2025:1-5.
[13]PAPADOPOULOS S,KOUKIOU G,ANASTAS SOPOULOS V.Decision fusion at pixel level of multi-band data for land cover classificationa review[J].Journal of Imaging,2024,10(1):15.
[14]BALDWIN C Y,CLARK K B.Design rules:the power of modularity[M].Cambridge:MIT Press,1999.
[15]HALL D L,LLINAS J.An introduction to multisensor data fusion[J].Proceedings of the IEEE,1997,85(1):6-23.
[16]SIMON H A.The architecture of complexity[J].Proceedings of the American Philosophical Society,1962,106(6):467-482.
[17]SHANNON C E.A mathematical theory of communication[J].The Bell System Technical Journal,1948,27(3):379-423.
[18]ALEXANDER C.Notes on the synthesis of form[M].Cambridge:Harvard University Press,1964.
[19]ZHANG X J,CHEN M J,LIU F,et al.MSSSHANet:Hyperspectral and multispectral image fusion algorithm based on multi-scale spatial-spectral hybrid attention network[J].Measurement Science and Technology,2025,3 6(3):03 5407.
[20]LYNCH N A.Distributed algorithms[M].San Francisco:Morgan Kaufmann Publishers,1996.
[21]HAKEN H.Information and self-organization:a macroscopic approach to complex sy stems[M].Berlin:Springer Science&Business Media,2006.
[22]HOLLAND JH.Complex adaptive systems[J].Daedalus,1992,121(1):17-30.
[23]VON BERTALANFFY L.General system theory:foundations,development,applications[M].New York:George Braziller,1968.
[24]KAUR J,RANI S,DOGRA A,et al.Pan sharpening techniques enhancing multi-spectral image resolution[C]//2024 5th International Conference on Smart Electronics and Communication,Trichy,India,September 18-20,2024:980-985.
[25]GELVEZ-B ARRERA T,ARGUELLO H,FOI A.Joint nonlocal,spectral,and similarity low-rank priors for hyperspectral-multispectral image fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:55 37112.
[26]FU X Y,JIA S,XU M,et al.Fusion of hyperspectral and multispectral images accounting for localized inter-image changes[J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:5517218.
[27]ZARE M,HELFROUSH M S,KAZEMI K,et al.Hyperspectral and multispectral image fusion using coupled non-negative Tucker tensor decomposition[J].Remote Sensing,2021,13(15):2930.
[28]MO C H,GUO H,CAO M,et al.Block term tensor decomposition multispectral and typerspectral fusion algorithm based on sparse regularization[J]Journal of Applied Remote Sensing,2024,18(4):048503.
[29]ZHANG X,HUANG W,WANG Q,et al.S SR-NET:spatial-spectral reconstruction network for hyperspectral and multispectral image fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2021,5 9(7):5953-5965.
[30]LIU X Y,LIU Q J,WANG Y H.Remote sensing image fusion based on two-stream fusion network[J].Information Fusion,2020,55:1-15.
[31]HU J F,HUANG T Z,DENG L J.Fusformer:a transformer-based fusion network for hyperspectral image super-resolution[J].IEEE Geoscience and Remote Sensing Letters,2022,19:60123 05.
[32]FENG Z Y,ZHANG X F,ZHOU B,et al.NGST-Net:a N-Gram based Swin Transformer Network for improving multispectral and hyperspectral image fusion[J].International Journal of Digital Earth,2024,17(1):23 59574.
[33]ZHU C Y,DENG S Q,LI J X,et al.Hyperspectral and multispectral remote sensing image fusion using SwinGAN with joint adaptive spatialspectral gradient loss function[J].International Journal of Digital Earth,2023,16(1):3 5 80-3600.
[34]LIU Z,HAN X H.Hyperspectral image super resolution using deep internal and self-supervised learning[J].CAAI Transactions on Intelligence Technology,2024,9(1):128-141.
[35]WANG Z C,NG MICHAEL K,MICHALSKI J,et al.A self-supervised deep denoiser for hyperspectral and multispectral image fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2023,61:5 520414.
[3 6]WANG H,XU Y,WU Z B,et al.Unsupervised hyperspectral and multispectral image blind fusion based on deep tucker decomposition network with spatial-spectral manifold learning[J].IEEE Transactions on Neural Networks and Learning Systems,2024,36(7):12721-12735.
[37]YU Y,PAN E T,WANG X Y,et al.Unmixing before fusion:a generalized paradigm for multi-source-based hyperspectral image synthesis[C]//2024IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR),Seattle,USA,June 16-22,2024:9297-9306.
[38]何泽平,许建,戴华,等.联邦学习应用技术研究综述[J].信息网络安全,2024,24(12):1831-1844
[39]陈涛,杨启亮,陈寅.神经辐射场技术及应用综述[J].计算机辅助设计与图形学学报,2025,37(1):51-74
[40]张鹏程,武文波,李强,等,面向星载边缘计算的遥感目标检测算法轻量化优化研究[J].空间控制技术与应用,2022,48(5):86-94
基本信息:
DOI：
中图分类号:TP751
引用信息:
[1]张星月,陈明举,胡潇,等.高光谱与多光谱图像融合技术综述[J].四川轻化工大学学报(自然科学版),2025,38(06):17-28.
基金信息:
四川省自然科学基金项目（2025ZNSFSC0477;2024NSFSC2042）; 四川轻化工大学研究生创新基金资助项目（Y2024297）