中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
High-resolution Solar Image Registration Using Unsupervised Deep Learning

文献类型:期刊论文

作者Zhang, Hao4; Liang, Bo4; Yan XL(闫晓理)2,3; Feng, Song4; Yuan, Ding1; Cai YF(蔡云芳)2,3; Dai, Wei4
刊名ASTROPHYSICAL JOURNAL
出版日期2025-08-01
卷号988期号:2
ISSN号0004-637X
DOI10.3847/1538-4357/adeb77
产权排序第2完成单位
文献子类Article
英文摘要High-resolution solar images captured at different wavelengths are essential for understanding solar activity. However, such images often exhibit geometric discrepancies due to varying instrument resolutions and observation conditions, making image registration a critical preprocessing step. In this study, we propose an unsupervised deep learning-based framework named hourGlass and haRdnEt (GRE) for accurate solar image registration. The method detects keypoints in both the reference and moving images, extracts local feature descriptors, performs bidirectional matching to establish reliable correspondences, and estimates affine transformation parameters to align the images. The proposed framework was evaluated on quiet Sun images from the New Vacuum Solar Telescope and active region (AR) images from the Goode Solar Telescope, covering both photospheric and chromospheric features. A synthetic data set with known transformations was also used to assess registration accuracy under controlled conditions. Registration performance was quantitatively measured using mutual information (MI) and structural similarity index (SSIM) methods, and results were compared with those obtained using the scale-invariant feature transform and intensity-based two-step methods. The experimental results demonstrate that the proposed method achieves accurate registration across different solar features and imaging scenarios. The method maintains structural consistency in both AR and quiet Sun observations, including time-series data, with MI and SSIM improvements over baseline methods. The approach provides a validated tool for solar image alignment, suitable for further solar physics studies.
学科主题天文学 ; 太阳与太阳系 ; 计算机科学技术 ; 人工智能
URL标识查看原文
出版地TEMPLE CIRCUS, TEMPLE WAY, BRISTOL BS1 6BE, ENGLAND
资助项目New Vacuum Solar Telescope (NVST) team; Open Fund of the Yunnan Key Laboratory of Computer Technologies Application
WOS研究方向Astronomy & Astrophysics
语种英语
WOS记录号WOS:001538578900001
出版者IOP Publishing Ltd
资助机构New Vacuum Solar Telescope (NVST) team ; Open Fund of the Yunnan Key Laboratory of Computer Technologies Application
版本出版稿
源URL[http://ir.ynao.ac.cn/handle/114a53/28475]  
专题云南天文台_抚仙湖太阳观测站
通讯作者Feng, Song
作者单位1.Institute of Space Science and Applied Technology, Harbin Institute of Technology, Shenzhen, Guangdong 518055, People’s Republic of China
2.Yunnan Key Laboratory of the Solar Physics and Space Science, Kunming 650216, People’s Republic of China;
3.Yunnan Observatories, Chinese Academy of Sciences, Kunming 650216, People’s Republic of China;
4.Faculty of Information Engineering and Automation, Kunming University of Science and Technology and Yunnan Key Laboratory of Computer Technologies Application, Kunming 650500, People’s Republic of China; feng.song@kust.edu.cn;
推荐引用方式
GB/T 7714
Zhang, Hao,Liang, Bo,Yan XL,et al. High-resolution Solar Image Registration Using Unsupervised Deep Learning[J]. ASTROPHYSICAL JOURNAL,2025,988(2).
APA Zhang, Hao.,Liang, Bo.,闫晓理.,Feng, Song.,Yuan, Ding.,...&Dai, Wei.(2025).High-resolution Solar Image Registration Using Unsupervised Deep Learning.ASTROPHYSICAL JOURNAL,988(2).
MLA Zhang, Hao,et al."High-resolution Solar Image Registration Using Unsupervised Deep Learning".ASTROPHYSICAL JOURNAL 988.2(2025).

入库方式: OAI收割

来源:云南天文台

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。