Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images

Cloud cover is a significant factor affecting the effectiveness of satellite-based Earth observations. Existing cloud detection algorithms primarily rely on imaging data from satellite sensors in the visible to near-infrared spectral range, making it challenging to achieve day-and-night cloud monito...

Full description

Saved in:
Bibliographic Details
Main Authors: Long Gao, Liyuan Li, Jianing Yu, Xiaoxuan Zhou, Lu Zou, Nan Fang, Xiaofeng Su, Fansheng Chen
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2024.2409966
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850284246250291200
author Long Gao
Liyuan Li
Jianing Yu
Xiaoxuan Zhou
Lu Zou
Nan Fang
Xiaofeng Su
Fansheng Chen
author_facet Long Gao
Liyuan Li
Jianing Yu
Xiaoxuan Zhou
Lu Zou
Nan Fang
Xiaofeng Su
Fansheng Chen
author_sort Long Gao
collection DOAJ
description Cloud cover is a significant factor affecting the effectiveness of satellite-based Earth observations. Existing cloud detection algorithms primarily rely on imaging data from satellite sensors in the visible to near-infrared spectral range, making it challenging to achieve day-and-night cloud monitoring. Convolutional neural networks have shown outstanding performance in previous cloud detection algorithms due to their robust ability to extract local information. However, their inherent inductive bias limits their capacity to learn long-range semantic information. To address these challenges, we proposed SwinCloud, a U-shaped semantic segmentation network based on an enhanced Swin Transformer for cloud detection in the thermal infrared spectral range. Specifically, we augment the Swin Transformer's window attention module with a CNN-based parallel pathway to effectively model global-local information. We employ a feature fusion module before the final upsampling module in the decoder to better integrate low-level spatial information and high-level semantic information. On the Landsat-8 cloud detection dataset, our model outperforms state-of-the-art methods. When transferred to the SDGSAT-TIS cloud detection dataset, the mIOU of experiment results reaches 69.9%, demonstrating the strong transferability of SwinCloud across different sensors. We also applied SwinCloud to cloud detection in the visible bands of Landsat-8. The results demonstrated SwinCloud's generalization capability across different bands.
format Article
id doaj-art-db16f457d4c34104a3f1b19a1ac627a4
institution OA Journals
issn 1753-8947
1753-8955
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-db16f457d4c34104a3f1b19a1ac627a42025-08-20T01:47:37ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552024-12-0117110.1080/17538947.2024.2409966Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing imagesLong Gao0Liyuan Li1Jianing Yu2Xiaoxuan Zhou3Lu Zou4Nan Fang5Xiaofeng Su6Fansheng Chen7Key Laboratory of Intelligent Infrared Perception, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, People’s Republic of ChinaShanghai Frontier Base of Intelligent Optoelectronics and Perception, Institute of Optoelectronics, Fudan University, Shanghai, People’s Republic of ChinaUniversity of Chinese Academy of Sciences, Beijing, People’s Republic of ChinaKey Laboratory of Intelligent Infrared Perception, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, People’s Republic of ChinaChina Xi’an Satellite Control Center, the State Key Laboratory of Astronautic Dynamics, Xi’an, People’s Republic of ChinaKey Laboratory of Intelligent Infrared Perception, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, People’s Republic of ChinaKey Laboratory of Intelligent Infrared Perception, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, People’s Republic of ChinaKey Laboratory of Intelligent Infrared Perception, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, People’s Republic of ChinaCloud cover is a significant factor affecting the effectiveness of satellite-based Earth observations. Existing cloud detection algorithms primarily rely on imaging data from satellite sensors in the visible to near-infrared spectral range, making it challenging to achieve day-and-night cloud monitoring. Convolutional neural networks have shown outstanding performance in previous cloud detection algorithms due to their robust ability to extract local information. However, their inherent inductive bias limits their capacity to learn long-range semantic information. To address these challenges, we proposed SwinCloud, a U-shaped semantic segmentation network based on an enhanced Swin Transformer for cloud detection in the thermal infrared spectral range. Specifically, we augment the Swin Transformer's window attention module with a CNN-based parallel pathway to effectively model global-local information. We employ a feature fusion module before the final upsampling module in the decoder to better integrate low-level spatial information and high-level semantic information. On the Landsat-8 cloud detection dataset, our model outperforms state-of-the-art methods. When transferred to the SDGSAT-TIS cloud detection dataset, the mIOU of experiment results reaches 69.9%, demonstrating the strong transferability of SwinCloud across different sensors. We also applied SwinCloud to cloud detection in the visible bands of Landsat-8. The results demonstrated SwinCloud's generalization capability across different bands.https://www.tandfonline.com/doi/10.1080/17538947.2024.2409966Cloud detectionSwin TransformerSDGSAT-1Landsat-8thermal infrared
spellingShingle Long Gao
Liyuan Li
Jianing Yu
Xiaoxuan Zhou
Lu Zou
Nan Fang
Xiaofeng Su
Fansheng Chen
Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images
International Journal of Digital Earth
Cloud detection
Swin Transformer
SDGSAT-1
Landsat-8
thermal infrared
title Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images
title_full Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images
title_fullStr Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images
title_full_unstemmed Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images
title_short Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images
title_sort swincloud a hybrid network for cloud detection in thermal infrared remote sensing images
topic Cloud detection
Swin Transformer
SDGSAT-1
Landsat-8
thermal infrared
url https://www.tandfonline.com/doi/10.1080/17538947.2024.2409966
work_keys_str_mv AT longgao swincloudahybridnetworkforclouddetectioninthermalinfraredremotesensingimages
AT liyuanli swincloudahybridnetworkforclouddetectioninthermalinfraredremotesensingimages
AT jianingyu swincloudahybridnetworkforclouddetectioninthermalinfraredremotesensingimages
AT xiaoxuanzhou swincloudahybridnetworkforclouddetectioninthermalinfraredremotesensingimages
AT luzou swincloudahybridnetworkforclouddetectioninthermalinfraredremotesensingimages
AT nanfang swincloudahybridnetworkforclouddetectioninthermalinfraredremotesensingimages
AT xiaofengsu swincloudahybridnetworkforclouddetectioninthermalinfraredremotesensingimages
AT fanshengchen swincloudahybridnetworkforclouddetectioninthermalinfraredremotesensingimages