SAR Image Despeckling by Noisy Reference-Based Deep Learning Method

SAR Image Despeckling by Noisy Reference-Based Deep Learning Method

Traditionally, clean reference images are needed to train the networks when applying the deep learning techniques to tackle image denoising tasks. However, this idea is impracticable for the task of synthetic aperture radar (SAR) image despeckling, since no real-world speckle-free SAR data exist. To address this issue, this article presents a noisy reference-based SAR deep learning filter, by using complementary images of the same area at different times as the training references. In the proposed method, to better exploit the information of the images, parameter-sharing convolutional neural networks are employed. Furthermore, to mitigate the training errors caused by the land-cover changes between different times, the similarity of each pixel pair between the different images is utilized to optimize the training process. The outstanding despeckling performance of the proposed method was confirmed by the experiments conducted on several multitemporal data sets, when compared with some of the state-of-the-art SAR despeckling techniques. In addition, the proposed method shows a pleasing generalization ability on single-temporal data sets, even though the networks are trained using finite input-reference image pairs at a different imaging area.

传统上，在应用深度学习技术解决图像去噪任务时，需要干净的参考图像来训练网络。然而，对于合成孔径雷达（SAR）图像去斑任务，这一想法是不切实际的，因为现实世界中不存在无斑点的SAR数据。为了解决这个问题，本文提出了一种基于含噪参考的SAR深度学习滤波器，通过使用同一区域在不同时间的互补图像作为训练参考。在所提出的方法中，为了更好地利用图像信息，采用了参数共享卷积神经网络。此外，为了减少由不同时间之间的土地覆盖变化引起的训练误差，利用不同图像之间每个像素对的相似性来优化训练过程。通过在多个多时相数据集上进行的实验，并与一些最先进的SAR去斑技术进行比较，证实了所提方法出色的去斑性能。此外，即使网络是使用在不同成像区域的有限输入 - 参考图像对进行训练的，所提方法在单时相数据集上也显示出良好的泛化能力。