A CNN-based Method for SAR Image Despeckling
Published in 2019 IEEE International Geoscience and Remote Sensing Symposium, 2019
Recommended citation: D. J. Ma, X. L. Zhang, X. X. Tang, J. Ming, et al. "A CNN-based Method for SAR Image Despeckling." IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing SymposiumYokohama, Japan, 2019, pp. 4272-4275. doi: 10.1109/IGARSS.2019.8899122 http://jingming2019.github.io/files/A-CNN-based-Method-for-SAR-Image-Despeckling.pdf
Abstract: In this paper, to remove the speckle noise of SAR images, we propose a modified method for SAR image despeckling based on Convolutional Neural Networks (CNNs). The network uses dilated convolutions for feature extraction, which can extend the receptive field and prevent too many layers that may result in computational burden and low efficiency. The network also uses residual learning to accelerate training procedure and improve performance for SAR image despeckling. Experimental results show that the proposed method achieve good performance for SAR image despeckling both on simulated and real data. And compared with the traditional despeckling methods, the proposed method has better performance and higher efficiency.
Recommended citation: D. J. Ma, X. L. Zhang, X. X. Tang, J. Ming, et al. "A CNN-based Method for SAR Image Despeckling." IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing SymposiumYokohama, Japan, 2019, pp. 4272-4275. doi: 10.1109/IGARSS.2019.8899122