CIRSM-Net: A Cyclic Registration Network for SAR and Optical Images
IEEE Transactions on Geoscience and Remote Sensing · 2025 · 63 · 1-19
DOI: 10.1109/tgrs.2025.3540258 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2025. Verfasst von Peng Wang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Optoelectronic Measurement and Intelligent Perception Zhongguancun Open Laboratory, Open Fund of Key Laboratory of Mine Environmental Monitoring and Improving Around Poyang Lake of Ministry of Natural Resources, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
The registration of synthetic aperture radar (SAR) and optical images is critical in multimodal remote sensing image fusion. In recent years, deep learning-based registration networks have been continuously introduced. However, owing to the significant disparities in viewing angles and radiometric properties between SAR and optical images, current deep learning methods struggle to fully exploit the physical properties of radar imaging. In addition, many existing matching networks typically perform only a forward pass, resulting in suboptimal model performance. This article proposes a cyclic iterative registration SAR mechanism network (termed as CIRSM-Net) for the registration of SAR and optical images. First, we design a learning module that integrates the radar equation with a microwave scattering model to capture deep features from SAR images, and design a corresponding scattering feature loss to aid in better generalization across various radar images. Then, to explore optimization methods for matching networks, this study proposes a strategy of multiple iterative optimizations within the matching network. Specifically, it integrates speeding-up radiation-variation insensitive feature transform (RIFT2) supervision in the backend matching network and iteratively optimizes the final output. Finally, during the iteration process, we propose an innovative matching loss function that combines the rotation invariance supervision of RIFT2 with iterative optimization techniques to enhance feature matching accuracy. Experimental results on both public and our own datasets additionally confirm the effectiveness and superiority of the proposed approach, demonstrating its significant potential for practical applications.
Förderung
- Optoelectronic Measurement and Intelligent Perception Zhongguancun Open Laboratory
- Open Fund of Key Laboratory of Mine Environmental Monitoring and Improving Around Poyang Lake of Ministry of Natural Resources
- Shenzhen Science and Technology Program
- Shanghai Aerospace Science and Technology Innovation Foundation
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Postgraduate Research and Practice Innovation Program of Nanjing University of Aeronautics and Astronautics
- Graduate Education and Teaching Reform Research Project in Nanjing University of Aeronautics and Astronautics
Zitieren
APA
Wang, P., Liu, Y., Liang, X., Zhu, D., Gong, X., Ye, Y., Lee, H. F., & Huang, B. (2025). CIRSM-Net: A Cyclic Registration Network for SAR and Optical Images. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-19. https://doi.org/10.1109/tgrs.2025.3540258
Vancouver
Wang P, Liu Y, Liang X, Zhu D, Gong X, Ye Y, et al. CIRSM-Net: A Cyclic Registration Network for SAR and Optical Images. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1-19. doi:10.1109/tgrs.2025.3540258
BibTeX
@article{Wang2025,
author = {Wang, Peng and Liu, Yuzhou and Liang, Xiao and Zhu, Daiyin and Gong, Xunqiang and Ye, Yuanxin and Lee, Harry F. and Huang, Bo},
title = {CIRSM-Net: A Cyclic Registration Network for SAR and Optical Images},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
year = {2025},
volume = {63},
pages = {1--19},
doi = {10.1109/tgrs.2025.3540258}
}
EUVIMED