A Novel Spectral Indices-Driven Spectral-Spatial-Context Attention Network for Automatic Cloud Detection
Cloud detection is a fundamental step for optical satellite image applications. Existing deep learning methods can provide more accurate cloud detection results. However, the performance of these methods relies on a large number of label samples, whose collection is time-consuming and high-cost. In...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10078301/ |
_version_ | 1797330424932859904 |
---|---|
author | Yang Chen Luliang Tang Wumeng Huang Jianhua Guo Guang Yang |
author_facet | Yang Chen Luliang Tang Wumeng Huang Jianhua Guo Guang Yang |
author_sort | Yang Chen |
collection | DOAJ |
description | Cloud detection is a fundamental step for optical satellite image applications. Existing deep learning methods can provide more accurate cloud detection results. However, the performance of these methods relies on a large number of label samples, whose collection is time-consuming and high-cost. In addition, cloud detection is challenging in high-brightness scenes due to cloud and high-brightness objects having a similar spectral features. In this study, we propose a cloud index driven spectral-spatial-context attention network (SSCA-net) for cloud detection, which relies on no effort to manually collect label samples and can improve the accuracy of cloud detection in high-brightness scenes. The label samples are automatically generated from the cloud index by using dual-threshold, which is then expanded to improve the completeness of cloud mask labels. We designed SSCA-net with the spectral-spatial-context aware module and spectral-spatial-context information aggregation module, aimed to improve the accuracy of cloud detection in high-brightness scenes. The results show that the proposed SSCA-net achieved good performance with an average overall accuracy of 97.69% and an average kappa coefficient of 92.71% on the Sentinel-2 and Landsat-8 datasets. This article provides fresh insight into how advanced deep attention networks and cloud indexes can be integrated to obtain high accuracy of cloud detection on high-brightness scenes. |
first_indexed | 2024-03-08T07:19:39Z |
format | Article |
id | doaj.art-b4146d7e756343d6ade15745931371fe |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-03-08T07:19:39Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-b4146d7e756343d6ade15745931371fe2024-02-03T00:00:42ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01163092310310.1109/JSTARS.2023.326020310078301A Novel Spectral Indices-Driven Spectral-Spatial-Context Attention Network for Automatic Cloud DetectionYang Chen0https://orcid.org/0000-0002-3407-7845Luliang Tang1https://orcid.org/0000-0003-3523-8994Wumeng Huang2Jianhua Guo3Guang Yang4https://orcid.org/0000-0002-5882-9597Beidou Research Institute, Faculty of Engineering, South China Normal University, Foshan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaGuangzhou Institute of Geography, Guangdong Academy of Sciences, Guangzhou, ChinaDepartment of Aerospace and Geodesy, Data Science in Earth Observation, Technical University of Munich, Munich, GermanyBeidou Research Institute, Faculty of Engineering, South China Normal University, Foshan, ChinaCloud detection is a fundamental step for optical satellite image applications. Existing deep learning methods can provide more accurate cloud detection results. However, the performance of these methods relies on a large number of label samples, whose collection is time-consuming and high-cost. In addition, cloud detection is challenging in high-brightness scenes due to cloud and high-brightness objects having a similar spectral features. In this study, we propose a cloud index driven spectral-spatial-context attention network (SSCA-net) for cloud detection, which relies on no effort to manually collect label samples and can improve the accuracy of cloud detection in high-brightness scenes. The label samples are automatically generated from the cloud index by using dual-threshold, which is then expanded to improve the completeness of cloud mask labels. We designed SSCA-net with the spectral-spatial-context aware module and spectral-spatial-context information aggregation module, aimed to improve the accuracy of cloud detection in high-brightness scenes. The results show that the proposed SSCA-net achieved good performance with an average overall accuracy of 97.69% and an average kappa coefficient of 92.71% on the Sentinel-2 and Landsat-8 datasets. This article provides fresh insight into how advanced deep attention networks and cloud indexes can be integrated to obtain high accuracy of cloud detection on high-brightness scenes.https://ieeexplore.ieee.org/document/10078301/Cloud detectioncloud index (CI)remote sensing imagespectral-spatial-context attention |
spellingShingle | Yang Chen Luliang Tang Wumeng Huang Jianhua Guo Guang Yang A Novel Spectral Indices-Driven Spectral-Spatial-Context Attention Network for Automatic Cloud Detection IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Cloud detection cloud index (CI) remote sensing image spectral-spatial-context attention |
title | A Novel Spectral Indices-Driven Spectral-Spatial-Context Attention Network for Automatic Cloud Detection |
title_full | A Novel Spectral Indices-Driven Spectral-Spatial-Context Attention Network for Automatic Cloud Detection |
title_fullStr | A Novel Spectral Indices-Driven Spectral-Spatial-Context Attention Network for Automatic Cloud Detection |
title_full_unstemmed | A Novel Spectral Indices-Driven Spectral-Spatial-Context Attention Network for Automatic Cloud Detection |
title_short | A Novel Spectral Indices-Driven Spectral-Spatial-Context Attention Network for Automatic Cloud Detection |
title_sort | novel spectral indices driven spectral spatial context attention network for automatic cloud detection |
topic | Cloud detection cloud index (CI) remote sensing image spectral-spatial-context attention |
url | https://ieeexplore.ieee.org/document/10078301/ |
work_keys_str_mv | AT yangchen anovelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection AT luliangtang anovelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection AT wumenghuang anovelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection AT jianhuaguo anovelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection AT guangyang anovelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection AT yangchen novelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection AT luliangtang novelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection AT wumenghuang novelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection AT jianhuaguo novelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection AT guangyang novelspectralindicesdrivenspectralspatialcontextattentionnetworkforautomaticclouddetection |