Generative Adversarial Networks for Remote Sensing

Generative adversarial networks (GANs) have been increasingly popular among deep learning methods. With many GANs-based models developed since its emergence, among which are conditional generative adversarial networks, progressive growing of generative adversarial networks, Wasserstein generative adversarial networks and so on. These frameworks are currently widely applied in areas such as remote sensing cybersecurity, medical, and architecture. Especially, they have solved problems of cloud removal, semantic segmentation, image-to-image translation and data argumentation in remote sensing. For example, WGANs and ProGANs can be applied in data argumentation, and cGANs can be applied in semantic argumentation and image-to-image translation. This article provides an overview of structures of multiple GANs-based models and what areas they can be applied in remote sensing.

I. Introduction

Remote sensing is a detection technic that does not need the user to contact the objection or detect the objection within a short distance. At present, remote sensing has developed to system with multi-level, multi-perspective, and multi-area observation. Remote sensing can be used to comprehensive detection and monitoring from the ground to the air. Apart from these, the application of remote sensing varies from information data collection and helps with interpretation analysis. It has developed a significant method of obtaining information on earth resources and environment. Aiming to improve the processing speed of such a large amount of data, remote sensing digital image technology has developed rapidly. Over the next decade, remote sensing technology is expected to enter a new phase in which multiple Earth observation data can be made available quickly and in a timely manner. As space technology developed, especially the growth and mutual penetration of geographic information systems and global positioning system technology, the application areas of remote sensing will become more and more extensive.