Cloud removal in remote sensing images using generative adversarial networks and SAR-to-optical image translation
This work provides an incremental improvement in cloud removal from satellite images, which is beneficial for remote sensing applications that rely on clear optical imagery.
This paper addresses the problem of cloud removal in satellite images, especially for thick clouds, by employing two cascaded Generative Adversarial Networks (GANs). The first GAN translates Synthetic Aperture Radar (SAR) images to optical images, and the second GAN uses these translated images to remove clouds. The proposed method achieves more accurate results compared to state-of-the-art deep learning models in both SAR-to-optical translation and cloud removal.
Satellite images are often contaminated by clouds. Cloud removal has received much attention due to the wide range of satellite image applications. As the clouds thicken, the process of removing the clouds becomes more challenging. In such cases, using auxiliary images such as near-infrared or synthetic aperture radar (SAR) for reconstructing is common. In this study, we attempt to solve the problem using two generative adversarial networks (GANs). The first translates SAR images into optical images, and the second removes clouds using the translated images of prior GAN. Also, we propose dilated residual inception blocks (DRIBs) instead of vanilla U-net in the generator networks and use structural similarity index measure (SSIM) in addition to the L1 Loss function. Reducing the number of downsamplings and expanding receptive fields by dilated convolutions increase the quality of output images. We used the SEN1-2 dataset to train and test both GANs, and we made cloudy images by adding synthetic clouds to optical images. The restored images are evaluated with PSNR and SSIM. We compare the proposed method with state-of-the-art deep learning models and achieve more accurate results in both SAR-to-optical translation and cloud removal parts.