A Cloud Detection Method with Domain Adaptation Enhanced Generalization Capability

DAI Peiyu; LI Shizhong; JI Shunping; REN Ni

doi:10.13203/j.whugis20220435

您当前的位置：

首页 >

文章列表页 >

A Cloud Detection Method with Domain Adaptation Enhanced Generalization Capability

Photogrammetry and Remote Sensing | 更新时间：2026-11-05

- A Cloud Detection Method with Domain Adaptation Enhanced Generalization Capability
- Geomatics and Information Science of Wuhan University Vol. 50, Issue 1, Pages: 110-119(2025)
- 作者机构：
  
  1.江苏省农业科学院，江苏南京，210018
  2.中国资源卫星应用中心，北京，100094
  3.武汉大学遥感信息工程学院，湖北武汉，430079
- 作者简介：
- 基金信息：
- DOI：10.13203/j.whugis20220435
  CLC： P237
- Received：05 March 2023，
  
  Published：05 January 2025
- 稿件说明：
移动端阅览
戴佩玉,李世忠,季顺平，等.一种基于域自适应泛化增强的云检测方法[J].武汉大学学报（信息科学版）,2025,50(1):110-119.

DAI Peiyu,LI Shizhong,JI Shunping,et al.A Cloud Detection Method with Domain Adaptation Enhanced Generalization Capability[J].Geomatics and Information Science of Wuhan University,2025,50(1):110-119.
戴佩玉,李世忠,季顺平，等.一种基于域自适应泛化增强的云检测方法[J].武汉大学学报（信息科学版）,2025,50(1):110-119. DOI：10.13203/j.whugis20220435

DAI Peiyu,LI Shizhong,JI Shunping,et al.A Cloud Detection Method with Domain Adaptation Enhanced Generalization Capability[J].Geomatics and Information Science of Wuhan University,2025,50(1):110-119. DOI：10.13203/j.whugis20220435

摘要

由于遥感传感器光谱范围、成像条件、成像时间等差异，不同传感器获得的遥感影像之间普遍存在着色彩和光谱差异，导致利用开源数据集预训练的云检测模型往往难以直接应用于当前目标影像的云检测任务。提出了一种基于域自适应的云检测方法，实现目标数据集遥感影像与现有训练数据集影像之间的光谱映射，使得不同传感器、不同地理区域的目标数据集与训练数据集尽可能相似，以提高深度学习模型的泛化能力，以及预训练云检测模型在实际应用中的鲁棒性。具体地，所提的基于域自适应的云检测框架以一种基于卷积神经元网络的云检测模型作为预测算法，以循环生成对抗网络作为源域和目标域影像之间的光谱迁移算法。在全球范围内分布的高分二号、陆地卫星（land satellite，Landsat）7、Landsat 8等数据间的跨域实验，证明了所提方法的有效性和先进性。

Abstract

Objectives

Due to the differences in spectral range

imaging conditions and imaging time of remote sensing sensors

there are usually color and spectral differences between remote sensing images obtained by different sensors. Therefore

it is difficult to directly apply the model pretrained with open-source datasets for the cloud detection task on current target images.

Methods

A domain adaptive cloud detection algorithm is proposed

which realizes the spectral mapping between the target remote sensing images and the images of existing training datasets

and improves the generalization ability and robustness of the pretrained deep learning cloud detection model in practical applications. Specifically

the domain adaptation based cloud detection framework uses a convolutional neural network based cloud detection model as the prediction algorithm

and CycleGAN as the spectral domain transfer between images in the source domain and the target domain.

Results

The cross-domain experiments among Gaofen‑2

land satellite (Landsat) 7

Landsat 8 have proved the effectiveness and advance of the proposed method. (1) When the test dataset and training dataset are obtained from the same sensor

deep learning-based cloud detection algorithms obtain better results than the traditional cloud detection algorithms. (2) When cloud detection models trained on images from the source dataset are directly used to detect test images of the target dataset

the accuracy decreases obviously. (3) When the test images are pre-transformed by the introduced domain transfer algorithm

the accuracy of the cloud detection results is significantly improved and much better than the traditional methods. In addition

we discovered that when the spectral range of source training images covers the spectral range of test images

the accuracy of the cloud detection results decreases only slightly

but in the opposite case

the accuracy of the cloud detection results decreases significantly.

Conclusions

Domain transfer can map images between the test dataset and the training dataset at the pixel level

so that the distributions of them are similar both in spectral and spatial space. By introducing domain adaptation

the deep learning-based cloud detection method can make full use of the pre-trained models from existing datasets

which greatly reduces the demand on preparation of target labels.

关键词

Keywords

references

ZHANG Y C ， ROSSOW W B ， LACIS A A ， et al . Calculation of Radiative Fluxes from the Surface to Top of Atmosphere Based on ISCCP and Other Global Data Sets： Refinements of the Radiative Transfer Model and the Input Data ［J］. Journal of Geophysical Research （Atmospheres）， 2004 ， 109 （ D19 ）： D19105 .

MINNIS P ， TREPTE Q Z ， SUN-MACK S ， et al . Cloud Detection in Nonpolar Regions for CERES Using TRMM VIRS and Terra and Aqua MODIS Data ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2008 ， 46 （ 11 ）： 3857 - 3884 .

BIAN J H ， LI A N ， LIU Q N ， et al . Cloud and Snow Discrimination for CCD Images of HJ-1A/B Constellation Based on Spectral Signature and Spatio-Temporal Context ［J］. Remote Sensing ， 2016 ， 8 （ 1 ）： 31 .

ZHU X L ， HELMER E H . An Automatic Method for Screening Clouds and Cloud Shadows in Optical Satellite Image Time Series in Cloudy Regions ［J］. Remote Sensing of Environment ， 2018 ， 214 ： 135 - 153 .

GOODWIN N R ， COLLETT L J ， DENHAM R J ， et al . Cloud and Cloud Shadow Screening Across Queensland， Australia： An Automated Method for Landsat TM/ETM+ Time Series ［J］. Remote Sensing of Environment ， 2013 ， 134 ： 50 - 65 .

IRISH R R ， BARKER J L ， GOWARD S N ， et al . Characterization of the Landsat-7 ETM+ Automated Cloud-Cover Assessment （ACCA） Algorithm ［J］. Photogrammetric Engineering & Remote Sensing ， 2006 ， 72 （ 10 ）： 1179 - 1188 .

康一飞，潘励，孙明伟，等 . 基于高斯混合模型法的国产高分辨率卫星影像云检测［J］. 武汉大学学报（信息科学版）， 2017 ， 42 （ 6 ）： 782 - 788 .

KANG Yifei ， PAN Li ， SUN Mingwei ， et al . Gaussian Mixture Model Based Cloud Detection for Chinese High Resolution Satellite Imagery ［J］. Geomatics and Information Science of Wuhan University ， 2017 ， 42 （ 6 ）： 782 - 788 .

文雄飞，董新奕，刘良明 . “云指数法” 云检测研究［J］. 武汉大学学报（信息科学版）， 2009 ， 34 （ 7 ）： 838 - 841 .

WEN Xiongfei ， DONG Xinyi ， LIU Liangming . Cloud Index Method for Cloud Detection ［J］. Geomatics and Information Science of Wuhan University ， 2009 ， 34 （ 7 ）： 838 - 841 .

秦永，付仲良，周凡，等 . 一种利用TM影像自动检测云层的方法［J］. 武汉大学学报（信息科学版）， 2014 ， 39 （ 2 ）： 234 - 238 .

QIN Yong ， FU Zhongliang ， ZHOU Fan ， et al . A Method of Automatic Cloud Detection Using TM Image ［J］. Geomatics and Information Science of Wuhan University ， 2014 ， 39 （ 2 ）： 234 - 238 .

DI VITTORIO A V ， EMERY W J . An Automated， Dynamic Threshold Cloud-Masking Algorithm for Daytime AVHRR Images over Land ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2002 ， 40 （ 8 ）： 1682 - 1694 .

LUO Y ， TRISHCHENKO A P ， KHLOPENKOV K V . Developing Clear-Sky， Cloud and Cloud Shadow Mask for Producing Clear-Sky Composites at 250-meter Spatial Resolution for the Seven MODIS Land Bands over Canada and North America ［J］. Remote Sensing of Environment ， 2008 ， 112 （ 12 ）： 4167 - 4185 .

MELGANI F . Contextual Reconstruction of Cloud-Contaminated Multitemporal Multispectral Images ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2006 ， 44 （ 2 ）： 442 - 455 .

FISHER A . Cloud and Cloud-Shadow Detection in SPOT5 HRG Imagery with Automated Morphological Feature Extraction ［J］. Remote Sensing ， 2014 ， 6 （ 1 ）： 776 - 800 .

李微，方圣辉，佃袁勇，等 . 基于光谱分析的MODIS云检测算法研究［J］. 武汉大学学报（信息科学版）， 2005 ， 30 （ 5 ）： 435 - 438 .

LI Wei ， FANG Shenghui ， DIAN Yuanyong ， et al . Cloud Detection in MODIS Data Based on Spectrum Analysis ［J］. Geomatics and Information Science of Wuhan University ， 2005 ， 30 （ 5 ）： 435 - 438 .

ZHU Z ， WOODCOCK C E . Object-Based Cloud and Cloud Shadow Detection in Landsat Imagery ［J］. Remote Sensing of Environment ， 2012 ， 118 ： 83 - 94 .

QIU S ， HE B B ， ZHU Z ， et al . Improving Fmask Cloud and Cloud Shadow Detection in Mountainous Area for Landsats 4-8 Images ［J］. Remote Sensing of Environment ， 2017 ， 199 ： 107 - 119 .

FRANTZ D ， HAß E ， UHL A ， et al . Improvement of the Fmask Algorithm for Sentinel-2 Images： Separating Clouds from Bright Surfaces Based on Parallax Effects ［J］. Remote Sensing of Environment ， 2018 ， 215 ： 471 - 481 .

QIU S ， ZHU Z ， HE B B . Fmask 4.0： Improved Cloud and Cloud Shadow Detection in Landsats 4–8 and Sentinel-2 Imagery ［J］. Remote Sensing of Environment ， 2019 ， 231 ： 111205 .

LI Z W ， SHEN H F ， LI H F ， et al . Multi-feature Combined Cloud and Cloud Shadow Detection in GaoFen-1 Wide Field of View Imagery ［J］. Remote Sensing of Environment ， 2017 ， 191 ： 342 - 358 .

MATEO-GARCÍA G ， GÓMEZ-CHOVA L ， CAMPS-VALLS G . Convolutional Neural Networks for Multispectral Image Cloud Masking ［C］// IEEE International Geoscience and Remote Sensing Symposium ， Fort Worth， USA ， 2017 .

XIE F Y ， SHI M Y ， SHI Z W ， et al . Multilevel Cloud Detection in Remote Sensing Images Based on Deep Learning ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ， 2017 ， 10 （ 8 ）： 3631 - 3640 .

LI Z W ， SHEN H F ， WEI Y C ， et al . Cloud Detection by Fusing Multi-scale Convolutional Features ［J］. ISPRS Annals of the Photogrammetry， Remote Sensing and Spatial Information Sciences ， 2018 ， 4 （ 3 ）： 149 - 152 .

YANG J Y ， GUO J H ， YUE H J ， et al . CDnet： CNN-Based Cloud Detection for Remote Sensing Imagery ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2019 ， 57 （ 8 ）： 6195 - 6211 .

GUO J H ， YANG J Y ， YUE H J ， et al . CDnetV2： CNN-Based Cloud Detection for Remote Sensing Imagery with Cloud-Snow Coexistence ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2021 ， 59 （ 1 ）： 700 - 713 .

SHAO Z F ， PAN Y ， DIAO C Y ， et al . Cloud Detection in Remote Sensing Images Based on Multiscale Features-Convolutional Neural Network ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2019 ， 57 （ 6 ）： 4062 - 4076 .

LI Y S ， CHEN W ， ZHANG Y J ， et al . Accurate Cloud Detection in High-Resolution Remote Sensing Imagery by Weakly Supervised Deep Learning ［J］. Remote Sensing of Environment ， 2020 ， 250 ： 112045 .

JI S P ， DAI P Y ， LU M ， et al . Simultaneous Cloud Detection and Removal from Bitemporal Remote Sensing Images Using Cascade Convolutional Neural Networks ［J］. IEEE Transactions on Geoscien‑ce and Remote Sensing ， 2021 ， 59 （ 1 ）： 732 - 748 .

LUO C ， FENG S S ， YANG X F ， et al . LWCDnet： A Lightweight Network for Efficient Cloud Detection in Remote Sensing Images ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2022 ， 60 ： 5409816 .

LI W W ， ZHANG F ， LIN H ， et al . Cloud Detection and Classification Algorithms for Himawari-8 Imager Measurements Based on Deep Learning ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2022 ， 60 ： 4107117 .

WIELAND M ， LI Y ， MARTINIS S . Multi-sensor Cloud and Cloud Shadow Segmentation with a Convolutional Neural Network ［J］. Remote Sensing of Environment ， 2019 ， 230 ： 111203 .

MATEO-GARCÍA G ， LAPARRA V ， LÓPEZ-PUIGDOLLERS D ， et al . Transferring Deep Learning Models for Cloud Detection Between Landsat-8 and Proba-V ［J］. ISPRS Journal of Photogrammetry and Remote Sensing ， 2020 ， 160 ： 1 - 17 .

ZHU J Y ， PARK T ， ISOLA P ， et al . Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks ［C］// IEEE International Conference on Computer Vision ， Venice， Italy ， 2017 .

FOGA S ， SCARAMUZZA P L ， GUO S ， et al . Cloud Detection Algorithm Comparison and Validation for Operational Landsat Data Products ［J］. Remote Sensing of Environment ， 2017 ， 194 ： 379 - 390 .

RONNEBERGER O ， FISCHER P ， BROX T . U-Net： Convolutional Networks for Biomedical Image Segmentation ［C］// International Conference on Medical Image Computing and Computer-Assisted Intervention ， Munich， Germany ， 2015 .

TSAI Y H ， HUNG W C ， SCHULTER S ， et al . Learning to Adapt Structured Output Space for Semantic Segmentation ［C］// IEEE/CVF Conference on Computer Vision and Pattern Recognition ， Salt Lake City， USA ， 2018 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Information Entropy Uncertainty Estimation Based Domain Adaptation for Land Cover Classification from Multi-source Remote Sensing Images

Spatiotemporal Evolution and Explainable Analysis of Grassland Vulnerability in the Hohhot-Baotou-Ordos-Yulin Urban Agglomeration

Research Progress in Spatiotemporal Modeling， Analysis， and Prediction of Urban Activity Flows in Built Environment

Geometric and Frequency-Domain Constrained Single-Step Diffusion for Seabed Terrain Super-Resolution Reconstruction

A Framework for Evaluating Geospatial Cognitive Abilities of Multimodal Large Language Models for Brain-Inspired Spatial Intelligence

Related Author

WANG Dingpan

DONG Xiaohuan

HUANG Lingyong

WANG Xiaohua

LI Qingjun

Related Institution

State Key Laboratory of Geo‑information Engineering

Tianjin Institute of Surveying and Mapping Co. Ltd

AI问答

⁰