Satellite super-resolution images depending on deep learning methods: A comparative study

The deep learning neural network is a recent development that has become the subject of research in the computer vision and remote sensing disciplines. Super resolution (SR) images can be obtained using deep neural network methods that achieve a higher performance than all previous traditional methods. Here, in this study, the objective is to describe existing deep learning methods for SR satellite images. Different satellite data are used to predict the performance of each deep learning model. This article presents a brief overview of most deep learning techniques and compares them to obtain a more effective and efficient model. The deep network cascade model outperforms other deep learning algorithms; this algorithm is dependable in the reconstruction process for obtaining SR images and overcomes some drawbacks found in traditional reconstruction algorithms. The sparse coding network method remains valuable, and with some enhancements, further improvement in results can be achieved.