EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Synthetic Aperture Radar Image Despeckling Based on a Deep Learning Network Employing Frequency Domain Decomposition

Xueqing Zhao, Fuquan Ren, Haibo Sun, Qinghong Qi

Electronics · 2024-01-24 · 13 (3) · 490

DOI: 10.3390/electronics13030490 ↗

At a glance

Journal article in Electronics, published online on 2024-01-24. Written by Xueqing Zhao and 3 co-authors. Cited 19 times so far (Crossref); 53 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, Provincial Natural Science Foundation of Hebei, Science Research Project of the Hebei Education Department.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Synthetic aperture radar (SAR) images are inevitably interspersed with speckle noise due to their coherent imaging mechanism, which greatly hinders subsequent related research and application. In recent studies, deep learning has become an effective tool for despeckling remote sensing images. However, preserving more texture details while removing speckle noise remains a challenging task in the field of SAR image despeckling. Furthermore, most despeckling algorithms are designed specifically for a specific look and seriously lack generalizability. Therefore, in order to remove speckle noise in SAR images, a novel end-to-end frequency domain decomposition network (SAR−FDD) is proposed. The method first performs frequency domain decomposition to generate high-frequency and low-frequency information. In the high-frequency branch, a mean filter is employed to effectively remove noise. Then, an interactive dual-branch framework is utilized to learn the details and structural information of SAR images, effectively reducing speckles by fully utilizing features from different frequencies. In addition, a blind denoising model is trained to handle noisy SAR images with unknown noise levels. The experimental results demonstrate that the SAR−FDD achieves good visual effects and high objective evaluation metrics on both simulated and real SAR test sets (peak signal-to-noise ratio (PSNR): 27.59 ± 1.57 and structural similarity index (SSIM): 0.78 ± 0.05 for different speckle noise levels), demonstrating its strong denoising performance and ability to preserve edge textures.

Funding

  • National Natural Science Foundation of China
  • Provincial Natural Science Foundation of Hebei
  • Science Research Project of the Hebei Education Department

Cite

APA

Zhao, X., Ren, F., Sun, H., & Qi, Q. (2024). Synthetic Aperture Radar Image Despeckling Based on a Deep Learning Network Employing Frequency Domain Decomposition. Electronics, 13(3), 490. https://doi.org/10.3390/electronics13030490

Vancouver

Zhao X, Ren F, Sun H, Qi Q. Synthetic Aperture Radar Image Despeckling Based on a Deep Learning Network Employing Frequency Domain Decomposition. Electronics. 2024;13(3):490. doi:10.3390/electronics13030490

BibTeX
@article{Zhao2024,
  author = {Zhao, Xueqing and Ren, Fuquan and Sun, Haibo and Qi, Qinghong},
  title = {Synthetic Aperture Radar Image Despeckling Based on a Deep Learning Network Employing Frequency Domain Decomposition},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {3},
  pages = {490},
  doi = {10.3390/electronics13030490}
}
Start for free →