Diffusion-based relative radiometric normalization for multi-temporal remote sensing imagery

SONG Liyao; LIU Chunyan; LI Haiwei

doi:10.37188/CJLCD.2026-0028

您当前的位置：

首页 >

文章列表页 >

Diffusion-based relative radiometric normalization for multi-temporal remote sensing imagery

Image Processing | 更新时间：2026-09-12

- Diffusion-based relative radiometric normalization for multi-temporal remote sensing imagery
- Chinese Journal of Liquid Crystals and Displays Vol. 41, Issue 4, Pages: 592-604(2026)
- 作者机构：
  
  1.西安工业大学计算机科学与工程学院，陕西西安 710021
  2.中国科学院西安光学精密机械研究所，陕西西安 710119
- 作者简介：
- 基金信息：
  
  2024 Provincial-Level Approval of College Students' Innovation Program Project(S202410702086);National Key Research and Development Program of China(2022YFF1300201);General Special Scientific Research Program Project of the Shaanxi Provincial Department of Education(24JK0481);Natural Science Foundation of Shaanxi Province(2025JC-YBQN-366;2025JC-YBMS-256);the Open Research Fund of Shaanxi Key Laboratory of Optical Remote Sensing and Intelligent Information Processing(KF20250402);Xi'an Natural Science Foundation Project - General Project(2025JH-ZRKX-0150)
- DOI：10.37188/CJLCD.2026-0028
  CLC： TP751
- CSTR：32172.14.CJLCD.2026-0028
- Received：06 March 2026，
  
  Revised：2026-03-18，
  
  Published：05 April 2026
- 稿件说明：
移动端阅览
SONG Liyao, LIU Chunyan, LI Haiwei. Diffusion-based relative radiometric normalization for multi-temporal remote sensing imagery[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(4): 592-604.
DOI：

SONG Liyao, LIU Chunyan, LI Haiwei. Diffusion-based relative radiometric normalization for multi-temporal remote sensing imagery[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(4): 592-604. DOI： 10.37188/CJLCD.2026-0028. CSTR： 32172.14.CJLCD.2026-0028.

摘要

相对辐射归一化是多时相遥感分析的基础技术，但传统方法在处理非线性畸变、异常值干扰及异质地表覆盖条件时往往存在局限性。针对这些挑战，本文提出了一种基于扩散的概率框架，将辐射不一致性建模为确定性残差与随机扰动的组合。在该框架中，前向过程通过结构化噪声与随机噪声的叠加模拟辐射畸变的多源特性，而后向过程则依托双目标变分优化策略，在重建辐射一致性的同时保留原始影像的细节特征，从而在数学层面上实现了对复杂辐射畸变的精细化建模。其核心设计是空间-光谱注意力网络，该网络通过融合空间与光谱双注意力模块，在特征提取过程中动态强化关键波段响应与局部纹理结构，实现对跨波段依赖关系和多尺度空间上下文的高效捕获。为进一步提升模型在复杂场景下的适应能力，研究设计了基于结构相似性指数的预处理策略，通过自动筛选稳定伪不变区域引导模型训练，有效降低地物变化带来的干扰，增强训练样本的代表性与模型收敛的稳定性。基于多时相哨兵2号数据集的综合实验表明，所提方法在定量评价指标上持续优于现有对比方法，不仅具备更高的辐射校正精度和光谱保真度，还在植被指数一致性和纹理细节保留方面展现出显著优势。综上，该扩散驱动网络为大规模遥感影像相对辐射归一化提供了一种实践适应性的解决方案，未来可进一步拓展至多传感器融合与时间序列分析等应用场景。

Abstract

Relative radiometric normalization is a fundamental technique in multi-temporal remote sensing analysis， yet traditional methods often face limitations when dealing with nonlinear distortions， outlier interference， and heterogeneous land-cover conditions. To address these challenges， this paper proposes a diffusion-based probabilistic framework that models radiometric inconsistency as a combination of deterministic residuals and stochastic perturbations. Within this framework， the forward process simulates the multi-source characteristics of radiometric distortions through the superposition of structured and random noise， while the reverse process relies on a dual-objective variational optimization strategy to reconstruct radiometric consistency while preserving the detailed features of the original imagery， thereby achieving refined modeling of complex radiometric distortions at the mathematical level. Its core design is a spatial-spectral attention network， which integrates spatial and spectral attention modules to dynamically enhance key spectral band responses and local texture structures during feature extraction， enabling efficient capture of cross-band dependencies and multi-scale spatial context. To further improve the model’s adaptability in complex scenes， a preprocessing strategy based on the structural similarity index （SSIM） is designed. By automatically selecting stable pseudo-invariant regions to guide model training， it effectively reduces interference from land-cover changes and enhances the representativeness of training samples and the stability of model convergence. Comprehensive experiments on multi-temporal Sentinel-2 datasets demonstrate that the proposed method consistently outperforms existing comparative approaches in quantitative evaluation metrics. It not only achieves higher radiometric correction accuracy and spectral fidelity but also exhibits significant advantages in vegetation index consistency and texture detail preservation. In summary， this diffusion-driven network provides a practically adaptable solution for large-scale relative radiometric normalization of remote sensing imagery， and can be further extended to applications such as multi-sensor fusion and time series analysis in the future.

关键词

Keywords

references

HUI Y M ， XU B ， HUANG H B ， et al . Modelling spatial-temporal change of Poyang Lake using multitemporal Landsat imagery ［J］. International Journal of Remote Sensing ， 2008 ， 29 （ 20 ）： 5767 - 5784 . doi: 10.1080/01431160802060912 http://dx.doi.org/10.1080/01431160802060912

BOVOLO F ， BRUZZONE L . A theoretical framework for unsupervised change detection based on change vector analysis in the polar domain ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2007 ， 45 （ 1 ）： 218 - 236 . doi: 10.1109/tgrs.2006.885408 http://dx.doi.org/10.1109/tgrs.2006.885408

GHOSH A ， MISHRA N S ， GHOSH S . Fuzzy clustering algorithms for unsupervised change detection in remote sensing images ［J］. Information Sciences ， 2011 ， 181 （ 4 ）： 699 - 715 . doi: 10.1016/j.ins.2010.10.016 http://dx.doi.org/10.1016/j.ins.2010.10.016

VICENTE-SERRANO S M ， PÉREZ-CABELLO F ， LASANTA T . Assessment of radiometric correction techniques in analyzing vegetation variability and change using time series of Landsat images ［J］. Remote Sensing of Environment ， 2008 ， 112 （ 10 ）： 3916 - 3934 . doi: 10.1016/j.rse.2008.06.011 http://dx.doi.org/10.1016/j.rse.2008.06.011

ZHANG Y J ， YU L ， SUN M W ， et al . A mixed radiometric normalization method for mosaicking of high-resolution satellite imagery ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2017 ， 55 （ 5 ）： 2972 - 2984 . doi: 10.1109/tgrs.2017.2657582 http://dx.doi.org/10.1109/tgrs.2017.2657582

YAN N N ， WU B F ， BOKEN V K ， et al . A drought monitoring operational system for China using satellite data： design and evaluation ［J］. Geomatics， Natural Hazards and Risk ， 2016 ， 7 （ 1 ）： 264 - 277 . doi: 10.1080/19475705.2014.895964 http://dx.doi.org/10.1080/19475705.2014.895964

SCHULTZ M ， VERBESSELT J ， AVITABILE V ， et al . Error sources in deforestation detection using BFAST monitor on Landsat time series across three tropical sites ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ， 2016 ， 9 （ 8 ）： 3667 - 3679 . doi: 10.1109/jstars.2015.2477473 http://dx.doi.org/10.1109/jstars.2015.2477473

TEILLET P M . Image correction for radiometric effects in remote sensing ［J］. International Journal of Remote Sensing ， 1986 ， 7 （ 12 ）： 1637 - 1651 . doi: 10.1080/01431168608948958 http://dx.doi.org/10.1080/01431168608948958

YANG X J ， LO C P . Relative radiometric normalization performance for change detection from multi-date satellite images ［J］. Photogrammetric Engineering & Remote Sensing ， 2000 ， 66 （ 8 ）： 967 - 980 .

LIU S Q ， LIAN J ， ZHAN X C ， et al . Automatically eliminating seam lines with Poisson editing in complex relative radiometric normalization mosaicking scenarios ［J/OL］. arXiv ， 2021 ： 2106 . 07441 . doi: 10.48550/arXiv.2106.07441 http://dx.doi.org/10.48550/arXiv.2106.07441

LIU S Q ， WANG L ， LIAN J ， et al . Auto robust relative radiometric normalization via latent change noise modeling ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2024 ， 62 ： 5405415 . doi: 10.1109/tgrs.2024.3391175 http://dx.doi.org/10.1109/tgrs.2024.3391175

CHEN Y P ， SUN K M ， LI D R ， et al . Improved relative radiometric normalization method of remote sensing images for change detection ［J］. Journal of Applied Remote Sensing ， 2018 ， 12 （ 4 ）： 045018 . doi: 10.1117/1.jrs.12.045018 http://dx.doi.org/10.1117/1.jrs.12.045018

VERMOTE E F ， TANRÉ D ， DEUZE J L ， et al . Second simulation of the satellite signal in the solar spectrum， 6S： an overview ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 1997 ， 35 （ 3 ）： 675 - 686 . doi: 10.1109/36.581987 http://dx.doi.org/10.1109/36.581987

HALL F G ， STREBEL D E ， NICKESON J E ， et al . Radiometric rectification： toward a common radiometric response among multidate， multisensor images ［J］. Remote Sensing of Environment ， 1991 ， 35 （ 1 ）： 11 - 27 . doi: 10.1016/0034-4257(91)90062-b http://dx.doi.org/10.1016/0034-4257(91)90062-b

BAO N S ， LECHNER A M ， FLETCHER A ， et al . Comparison of relative radiometric normalization methods using pseudo-invariant features for change detection studies in rural and urban landscapes ［J］. Journal of Applied Remote Sensing ， 2012 ， 6 （ 1 ）： 063578 . doi: 10.1117/1.jrs.6.063578 http://dx.doi.org/10.1117/1.jrs.6.063578

SADEGHI V ， EBADI H ， AHMADI F F . A new model for automatic normalization of multitemporal satellite images using artificial neural network and mathematical methods ［J］. Applied Mathematical Modelling ， 2013 ， 37 （ 9 ）： 6437 - 6445 . doi: 10.1016/j.apm.2013.01.006 http://dx.doi.org/10.1016/j.apm.2013.01.006

ZHOU H Z ， LIU S M ， HE J J ， et al . A new model for the automatic relative radiometric normalization of multiple images with pseudo-invariant features ［J］. International Journal of Remote Sensing ， 2016 ， 37 （ 19 ）： 4554 - 4573 . doi: 10.1080/01431161.2016.1213922 http://dx.doi.org/10.1080/01431161.2016.1213922

TU Y H ， PHINN S ， JOHANSEN K ， et al . Assessing radiometric correction approaches for multi-spectral UAS imagery for horticultural applications ［J］. Remote Sensing ， 2018 ， 10 （ 11 ）： 1684 . doi: 10.3390/rs10111684 http://dx.doi.org/10.3390/rs10111684

HO J ， JAIN A ， ABBEEL P . Denoising diffusion probabilistic models ［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems . Vancouver ： Curran Associates Inc. ， 2020 ： 574 . doi: 10.48550/arXiv.2006.11239 http://dx.doi.org/10.48550/arXiv.2006.11239

卜丽静，陈香雪，张正鹏，等．基于两阶段残差条件扩散网络的遥感图像超分辨重建［J］．液晶与显示， 2025 ， 40 （ 11 ）： 1647 - 1660 ． doi: 10.37188/CJLCD.2025-0158 http://dx.doi.org/10.37188/CJLCD.2025-0158

BU L J ， CHEN X X ， ZHANG Z P ， et al . Two-stage residual conditional diffusion network for super-resolution reconstruction of remote sensing images ［J］. Chinese Journal of Liquid Crystals and Displays ， 2025 ， 40 （ 11 ）： 1647 - 1660 . （in Chinese） . doi: 10.37188/CJLCD.2025-0158 http://dx.doi.org/10.37188/CJLCD.2025-0158

赵晓，杜光磊．基于条件先验增强和扩散模型的遥感图像超分辨重建算法［J］．液晶与显示， 2025 ， 40 （ 7 ）： 1067 - 1079 ． doi: 10.37188/cjlcd.2025-0045 http://dx.doi.org/10.37188/cjlcd.2025-0045

ZHAO X ， DU G L . Super-resolution of remote sensing images based on conditional prior enhancement and diffusion models ［J］. Chinese Journal of Liquid Crystals and Displays ， 2025 ， 40 （ 7 ）： 1067 - 1079 . （in Chinese） . doi: 10.37188/cjlcd.2025-0045 http://dx.doi.org/10.37188/cjlcd.2025-0045

SALVAGGIO C . Radiometric scene normalization utilizing statistically invariant features ［C］// Proceedings of the Workshop on Atmospheric Correction of Landsat Imagery . Torrance， CA， USA ： USGS ， 1993 ： 155 - 159 .

毛红敏，丁致雅，杨燕燕，等．大气湍流对高分辨率遥感卫星的成像影响研究［J］. 中国光学（中英文）， 2024 ， 17 （ 1 ）： 167 - 177 ． doi: 10.37188/CO.2023-0083 http://dx.doi.org/10.37188/CO.2023-0083

MAO H M ， DING Z Y ， YANG Y Y ， et al . Effect of atmospheric turbulence on imaging quality of high-resolution remote sensing satellites ［J］. Chinese Optics ， 2024 ， 17 （ 1 ）： 167 - 177 . （in Chinese） . doi: 10.37188/CO.2023-0083 http://dx.doi.org/10.37188/CO.2023-0083

DU Y ， TEILLET P M ， CIHLAR J . Radiometric normalization of multitemporal high-resolution satellite images with quality control for land cover change detection ［J］. Remote Sensing of Environment ， 2002 ， 82 ： 123 - 134 . doi: 10.4095/219814 http://dx.doi.org/10.4095/219814

SONG J M ， MENG C L ， ERMON S . Denoising diffusion implicit models ［C］// Proceedings of the 9th International Conference on Learning Representations . Online ： OpenReview.net ， 2021 .

RICHARDS J A . Remote Sensing Digital Image Analysis ： An Introduction ［M］. 3rd ed . Berlin ： Springer ， 1999 . doi: 10.1007/978-3-662-03978-6 http://dx.doi.org/10.1007/978-3-662-03978-6

JENSEN J R . Urban / suburban land use analysis ［M］// Manual of Remote Sensing . 2nd ed . Falls Church ： Wiley ， 1983 ： 1571 - 1666 .

YA’ALLAH S M ， SARADJIAN M R . Automatic normalization of satellite images using unchanged pixels within urban areas ［J］. Information Fusion ， 2005 ， 6 （ 3 ）： 235 - 241 . doi: 10.1016/j.inffus.2004.12.002 http://dx.doi.org/10.1016/j.inffus.2004.12.002

HE H ， LIU X G ， SHEN Y L . Relative radiometric correction of high-resolution remote sensing images based on feature category ［J］. Cluster Computing ， 2019 ， 22 （ 4 ）： 7933 - 7941 . doi: 10.1007/s10586-017-1526-8 http://dx.doi.org/10.1007/s10586-017-1526-8

CANTY M J ， NIELSEN A A . Automatic radiometric normalization of multitemporal satellite imagery with the iteratively re-weighted MAD transformation ［J］. Remote Sensing of Environment ， 2008 ， 112 （ 3 ）： 1025 - 1036 . doi: 10.1016/j.rse.2007.07.013 http://dx.doi.org/10.1016/j.rse.2007.07.013

MALILA W A . Change vector analysis： an approach for detecting forest changes with Landsat ［C］// Proceedings of the LARS Symposium . Lafayette ： Purdue University ， 1980 ： 385 - 385 .

YUAN D ， ELVIDGE C D . Comparison of relative radiometric normalization techniques ［J］. ISPRS Journal of Photogrammetry and Remote Sensing ， 1996 ， 51 （ 3 ）： 117 - 126 . doi: 10.1016/0924-2716(96)00018-4 http://dx.doi.org/10.1016/0924-2716(96)00018-4

TANG L ， ZHAO X G ， HU X Q ， et al . A multi-task convolutional neural network relative radiometric calibration based on temporal information ［J］. Remote Sensing ， 2024 ， 16 （ 17 ）： 3346 . doi: 10.3390/rs16173346 http://dx.doi.org/10.3390/rs16173346

ZHU J Y ， PARK T ， ISOLA P ， et al . Unpaired image-to-image translation using cycle-consistent adversarial networks ［C］// Proceedings of the IEEE International Conference on Computer Vision （ICCV） . Venice ： IEEE ， 2017 ： 2223 - 2232 . doi: 10.1109/iccv.2017.244 http://dx.doi.org/10.1109/iccv.2017.244

Views

314

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Particle image velocimetry method based on ConvLSTM and LiteFlowNet architecture

3D hand reconstruction method based on adaptive occlusion recovery and topology-pose bidirectional perception

Fatigue driving detection based on improved YOLOv8n-Pose

Remote sensing scene classification model based on improved ShuffleNetV2 network

PCB defect detection based on ZYNQ and YOLO26n

Related Author

LIU Chunyan

LIU Xin'ai

MENG Juan

DU Hai

LI Zhiyuan

LIU Jia

HUANG Nanxuan

CHEN Dapeng

Related Institution

College of Information Engineering， Dalian Ocean University

State Key Laboratory of Coastal and Offshore Engineering， Dalian University of Technology

School of Automation， Nanjing University of Information Science & Technology

School of Computer and Computing Science， Hangzhou City University

School of Advanced Manufacturing， Fuzhou University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰