A Convolutional Neural Network SAR Image Denoising Algorithm Based on Self-Learning Strategies
Source abstract
Abstract
Due to its high resolution and all-weather imaging capability, Synthetic Aperture Radar (SAR) is widely used in fields such as Earth observation and environmental monitoring. However, SAR images are prone to noise interference during the imaging process, which seriously affects the visualization effect and subsequent analysis of the image. This article proposes a convolutional neural network SAR image denoising algorithm based on self-learning strategy. Particularly, a denoising convolutional neural network that utilizes a self-learning denoising model and a twin convolutional network structure is proposed. By constructing a noise original image dataset sample pair for training, the model can automatically learn image features and noise distribution, significantly improving the denoising effect of SAR images and possessing stronger generalization ability. The simulation experiments verified the effectiveness of the proposed method, indicating its potential application in SAR image denoising.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Algorithms and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
References (27)
Show source-provided references
1. Virtual Synthetic Aperture Radar Target Based on a Miniaturized Monostatic Digital Delay Transponder10.1109/LMWC.2021.3133660 ↗
2. Very high-resolution synthetic aperture radar systems and imaging: A review
3. MRDDANet: A Multiscale Residual Dense Dual Attention Network for SAR Image Denoising
4. SAR image compression with inherent denoising capability through knowledge distillation
5. PCENet: Deep SAR despeckling network using parallel convolutional encoding modules10.1109/LGRS.2023.3344684 ↗
6. A Review of Synthetic Aperture Radar Image Denoising Algorithms
7. SAR image despeckling based on nonlocal low-rank regularization10.1109/TGRS.2018.2885089 ↗
8. A tutorial on speckle reduction in synthetic aperture radar images10.1109/MGRS.2013.2277512 ↗
9. Research progress on SAR image speckle suppression
10. Iterative Weighted Maximum Likelihood Denoising with Probabilistic Patch-based Weights10.1109/TIP.2009.2029593 ↗
11. A Nonlocal SAR Image Denoising Algorithm Based on LLMMSE Wavelet Shrinkage10.1109/TGRS.2011.2161586 ↗
12. Liu, S., Hu, Q., Li, P., Zhao, J., Wang, C., and Zhu, Z. (2018). Speckle suppression based on sparse representation with nonrlocal priors. Remote Sens., 10.10.3390/rs10030439 ↗
13. Adaptive speckle filters and scene heterogeneity10.1109/36.62623 ↗
14. SAR despeckling based on CNN and Bayesian estimator in complex wavelet domain10.1109/LGRS.2022.3185557 ↗
15. SAR image despeckle with CNN using a novel logarithmic discrete cosine transform-based loss
16. HTCNet: Hybrid Transformer-CNN for SAR Image Denoising10.1109/JSTARS.2023.3281727 ↗
17. Segmentation-guided semantic-aware self-supervised denoising for SAR image
18. A CNN-based self-supervised synthetic aperture radar image denoising approach
19. Shin, S., Kim, Y., Hwang, I., Kim, J., and Kim, S. (2021). Coupling Denoising to Detection for SAR Imagery. Appl. Sci., 11.10.3390/app11125569 ↗
20. FFDNet: Toward a fast and flexible solution for CNN based image denoising10.1109/TIP.2018.2839891 ↗
21. Zheng, H., Yong, H., and Zhang, L. (2021). Deep convolutional dictionary learning for image denoising. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 11–15 June 2021, IEEE.10.1109/CVPR46437.2021.00069 ↗
22. Multilevel wavelet-SRNet for SAR target recognition
23. Wang, P., He, Z., and Patel, V.M. (2018). Generative adversarial network-based restoration of speckled SAR images. Curacao: IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Herradura, Costa Rica, 10–13 Decembrie 2018, IEEE.10.1109/CAMSAP.2017.8313133 ↗
24. Gu, F., Zhang, H., and Wang, C. (2019). A GAN-based method for SAR image despeckling. 2019 SAR in Big Data Era (BIGSARDATA), Beijing, China, 5–6 August 2019, IEEE.10.1109/BIGSARDATA.2019.8858487 ↗
25. Zhang, Q., and Sun, R. (2020). SAR Image Despeckling Based on Convolutional Denoising Autoencoder. arXiv.
26. PolMERLIN: Self-Supervised Polarimetric Complex SAR Image Despeckling with Masked Networks10.1109/LGRS.2024.3352544 ↗
27. A dual-path interactive denoising autoencoder for removing mixed noise in multi-lead electrocardiogram signals10.1016/j.compeleceng.2025.110177 ↗