Blind Deblurring of Remote-Sensing Single Images Based on Feature Alignment
Motion blur recovery is a common method in the field of remote sensing image processing that can effectively improve the accuracy of detection and recognition. Among the existing motion blur recovery methods, the algorithms based on deep learning do not rely on a priori knowledge and, thus, have bet...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/20/7894 |
| _version_ | 1797470026956013568 |
|---|---|
| author | Baoyu Zhu Qunbo Lv Yuanbo Yang Xuefu Sui Yu Zhang Yinhui Tang Zheng Tan |
| author_facet | Baoyu Zhu Qunbo Lv Yuanbo Yang Xuefu Sui Yu Zhang Yinhui Tang Zheng Tan |
| author_sort | Baoyu Zhu |
| collection | DOAJ |
| description | Motion blur recovery is a common method in the field of remote sensing image processing that can effectively improve the accuracy of detection and recognition. Among the existing motion blur recovery methods, the algorithms based on deep learning do not rely on a priori knowledge and, thus, have better generalizability. However, the existing deep learning algorithms usually suffer from feature misalignment, resulting in a high probability of missing details or errors in the recovered images. This paper proposes an end-to-end generative adversarial network (SDD-GAN) for single-image motion deblurring to address this problem and to optimize the recovery of blurred remote sensing images. Firstly, this paper applies a feature alignment module (FAFM) in the generator to learn the offset between feature maps to adjust the position of each sample in the convolution kernel and to align the feature maps according to the context; secondly, a feature importance selection module is introduced in the generator to adaptively filter the feature maps in the spatial and channel domains, preserving reliable details in the feature maps and improving the performance of the algorithm. In addition, this paper constructs a self-constructed remote sensing dataset (RSDATA) based on the mechanism of image blurring caused by the high-speed orbital motion of satellites. Comparative experiments are conducted on self-built remote sensing datasets and public datasets as well as on real remote sensing blurred images taken by an in-orbit satellite (CX-6(02)). The results show that the algorithm in this paper outperforms the comparison algorithm in terms of both quantitative evaluation and visual effects. |
| first_indexed | 2024-03-09T19:30:56Z |
| format | Article |
| id | doaj.art-a91153084a0c4c44be87d1c5a5f50a52 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T19:30:56Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a91153084a0c4c44be87d1c5a5f50a522023-11-24T02:28:01ZengMDPI AGSensors1424-82202022-10-012220789410.3390/s22207894Blind Deblurring of Remote-Sensing Single Images Based on Feature AlignmentBaoyu Zhu0Qunbo Lv1Yuanbo Yang2Xuefu Sui3Yu Zhang4Yinhui Tang5Zheng Tan6Aerospace Information Research Institute, Chinese Academy of Sciences, No.9 Dengzhuang South Road, Haidian District, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, No.9 Dengzhuang South Road, Haidian District, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, No.9 Dengzhuang South Road, Haidian District, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, No.9 Dengzhuang South Road, Haidian District, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, No.9 Dengzhuang South Road, Haidian District, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, No.9 Dengzhuang South Road, Haidian District, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, No.9 Dengzhuang South Road, Haidian District, Beijing 100094, ChinaMotion blur recovery is a common method in the field of remote sensing image processing that can effectively improve the accuracy of detection and recognition. Among the existing motion blur recovery methods, the algorithms based on deep learning do not rely on a priori knowledge and, thus, have better generalizability. However, the existing deep learning algorithms usually suffer from feature misalignment, resulting in a high probability of missing details or errors in the recovered images. This paper proposes an end-to-end generative adversarial network (SDD-GAN) for single-image motion deblurring to address this problem and to optimize the recovery of blurred remote sensing images. Firstly, this paper applies a feature alignment module (FAFM) in the generator to learn the offset between feature maps to adjust the position of each sample in the convolution kernel and to align the feature maps according to the context; secondly, a feature importance selection module is introduced in the generator to adaptively filter the feature maps in the spatial and channel domains, preserving reliable details in the feature maps and improving the performance of the algorithm. In addition, this paper constructs a self-constructed remote sensing dataset (RSDATA) based on the mechanism of image blurring caused by the high-speed orbital motion of satellites. Comparative experiments are conducted on self-built remote sensing datasets and public datasets as well as on real remote sensing blurred images taken by an in-orbit satellite (CX-6(02)). The results show that the algorithm in this paper outperforms the comparison algorithm in terms of both quantitative evaluation and visual effects.https://www.mdpi.com/1424-8220/22/20/7894remote sensingimage deblurringgenerative adversarial networksfeature alignmentfeature selectiondeep learning |
| spellingShingle | Baoyu Zhu Qunbo Lv Yuanbo Yang Xuefu Sui Yu Zhang Yinhui Tang Zheng Tan Blind Deblurring of Remote-Sensing Single Images Based on Feature Alignment Sensors remote sensing image deblurring generative adversarial networks feature alignment feature selection deep learning |
| title | Blind Deblurring of Remote-Sensing Single Images Based on Feature Alignment |
| title_full | Blind Deblurring of Remote-Sensing Single Images Based on Feature Alignment |
| title_fullStr | Blind Deblurring of Remote-Sensing Single Images Based on Feature Alignment |
| title_full_unstemmed | Blind Deblurring of Remote-Sensing Single Images Based on Feature Alignment |
| title_short | Blind Deblurring of Remote-Sensing Single Images Based on Feature Alignment |
| title_sort | blind deblurring of remote sensing single images based on feature alignment |
| topic | remote sensing image deblurring generative adversarial networks feature alignment feature selection deep learning |
| url | https://www.mdpi.com/1424-8220/22/20/7894 |
| work_keys_str_mv | AT baoyuzhu blinddeblurringofremotesensingsingleimagesbasedonfeaturealignment AT qunbolv blinddeblurringofremotesensingsingleimagesbasedonfeaturealignment AT yuanboyang blinddeblurringofremotesensingsingleimagesbasedonfeaturealignment AT xuefusui blinddeblurringofremotesensingsingleimagesbasedonfeaturealignment AT yuzhang blinddeblurringofremotesensingsingleimagesbasedonfeaturealignment AT yinhuitang blinddeblurringofremotesensingsingleimagesbasedonfeaturealignment AT zhengtan blinddeblurringofremotesensingsingleimagesbasedonfeaturealignment |