AIR-POLSAR-CR1.0: A Benchmark Dataset for Cloud Removal in High-Resolution Optical Remote Sensing Images with Fully Polarized SAR

Due to the all-time and all-weather characteristics of synthetic aperture radar (SAR) data, they have become an important input for optical image restoration, and various cloud removal datasets based on SAR-optical have been proposed. Currently, the construction of multi-source cloud removal dataset...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuxi Wang, Wenjuan Zhang, Jie Pan, Wen Jiang, Fangyan Yuan, Bo Zhang, Xijuan Yue, Bing Zhang
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/2/275
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832587579647590400
author Yuxi Wang
Wenjuan Zhang
Jie Pan
Wen Jiang
Fangyan Yuan
Bo Zhang
Xijuan Yue
Bing Zhang
author_facet Yuxi Wang
Wenjuan Zhang
Jie Pan
Wen Jiang
Fangyan Yuan
Bo Zhang
Xijuan Yue
Bing Zhang
author_sort Yuxi Wang
collection DOAJ
description Due to the all-time and all-weather characteristics of synthetic aperture radar (SAR) data, they have become an important input for optical image restoration, and various cloud removal datasets based on SAR-optical have been proposed. Currently, the construction of multi-source cloud removal datasets typically employs single-polarization or dual-polarization backscatter SAR feature images, lacking a comprehensive description of target scattering information and polarization characteristics. This paper constructs a high-resolution remote sensing dataset, AIR-POLSAR-CR1.0, based on optical images, backscatter feature images, and polarization feature images using the fully polarimetric synthetic aperture radar (PolSAR) data. The dataset has been manually annotated to provide a foundation for subsequent analyses and processing. Finally, this study performs a performance analysis of typical cloud removal deep learning algorithms based on different categories and cloud coverage on the proposed standard dataset, serving as baseline results for this benchmark. The results of the ablation experiment also demonstrate the effectiveness of the PolSAR data. In summary, AIR-POLSAR-CR1.0 fills the gap in polarization feature images and demonstrates good adaptability for the development of deep learning algorithms.
format Article
id doaj-art-8137cfb39fc34b0e969bdb828fdc3ff8
institution Kabale University
issn 2072-4292
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-8137cfb39fc34b0e969bdb828fdc3ff82025-01-24T13:47:58ZengMDPI AGRemote Sensing2072-42922025-01-0117227510.3390/rs17020275AIR-POLSAR-CR1.0: A Benchmark Dataset for Cloud Removal in High-Resolution Optical Remote Sensing Images with Fully Polarized SARYuxi Wang0Wenjuan Zhang1Jie Pan2Wen Jiang3Fangyan Yuan4Bo Zhang5Xijuan Yue6Bing Zhang7Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaDue to the all-time and all-weather characteristics of synthetic aperture radar (SAR) data, they have become an important input for optical image restoration, and various cloud removal datasets based on SAR-optical have been proposed. Currently, the construction of multi-source cloud removal datasets typically employs single-polarization or dual-polarization backscatter SAR feature images, lacking a comprehensive description of target scattering information and polarization characteristics. This paper constructs a high-resolution remote sensing dataset, AIR-POLSAR-CR1.0, based on optical images, backscatter feature images, and polarization feature images using the fully polarimetric synthetic aperture radar (PolSAR) data. The dataset has been manually annotated to provide a foundation for subsequent analyses and processing. Finally, this study performs a performance analysis of typical cloud removal deep learning algorithms based on different categories and cloud coverage on the proposed standard dataset, serving as baseline results for this benchmark. The results of the ablation experiment also demonstrate the effectiveness of the PolSAR data. In summary, AIR-POLSAR-CR1.0 fills the gap in polarization feature images and demonstrates good adaptability for the development of deep learning algorithms.https://www.mdpi.com/2072-4292/17/2/275remote sensingcloud removaldeep learningdatasetfull PolSAR
spellingShingle Yuxi Wang
Wenjuan Zhang
Jie Pan
Wen Jiang
Fangyan Yuan
Bo Zhang
Xijuan Yue
Bing Zhang
AIR-POLSAR-CR1.0: A Benchmark Dataset for Cloud Removal in High-Resolution Optical Remote Sensing Images with Fully Polarized SAR
Remote Sensing
remote sensing
cloud removal
deep learning
dataset
full PolSAR
title AIR-POLSAR-CR1.0: A Benchmark Dataset for Cloud Removal in High-Resolution Optical Remote Sensing Images with Fully Polarized SAR
title_full AIR-POLSAR-CR1.0: A Benchmark Dataset for Cloud Removal in High-Resolution Optical Remote Sensing Images with Fully Polarized SAR
title_fullStr AIR-POLSAR-CR1.0: A Benchmark Dataset for Cloud Removal in High-Resolution Optical Remote Sensing Images with Fully Polarized SAR
title_full_unstemmed AIR-POLSAR-CR1.0: A Benchmark Dataset for Cloud Removal in High-Resolution Optical Remote Sensing Images with Fully Polarized SAR
title_short AIR-POLSAR-CR1.0: A Benchmark Dataset for Cloud Removal in High-Resolution Optical Remote Sensing Images with Fully Polarized SAR
title_sort air polsar cr1 0 a benchmark dataset for cloud removal in high resolution optical remote sensing images with fully polarized sar
topic remote sensing
cloud removal
deep learning
dataset
full PolSAR
url https://www.mdpi.com/2072-4292/17/2/275
work_keys_str_mv AT yuxiwang airpolsarcr10abenchmarkdatasetforcloudremovalinhighresolutionopticalremotesensingimageswithfullypolarizedsar
AT wenjuanzhang airpolsarcr10abenchmarkdatasetforcloudremovalinhighresolutionopticalremotesensingimageswithfullypolarizedsar
AT jiepan airpolsarcr10abenchmarkdatasetforcloudremovalinhighresolutionopticalremotesensingimageswithfullypolarizedsar
AT wenjiang airpolsarcr10abenchmarkdatasetforcloudremovalinhighresolutionopticalremotesensingimageswithfullypolarizedsar
AT fangyanyuan airpolsarcr10abenchmarkdatasetforcloudremovalinhighresolutionopticalremotesensingimageswithfullypolarizedsar
AT bozhang airpolsarcr10abenchmarkdatasetforcloudremovalinhighresolutionopticalremotesensingimageswithfullypolarizedsar
AT xijuanyue airpolsarcr10abenchmarkdatasetforcloudremovalinhighresolutionopticalremotesensingimageswithfullypolarizedsar
AT bingzhang airpolsarcr10abenchmarkdatasetforcloudremovalinhighresolutionopticalremotesensingimageswithfullypolarizedsar