Generative-Network Based Multimedia Super-Resolution for Uav Remote Sensing

Abstract

Unmanned Aerial Vehicle (UAV) based aerial mapping has taken over the surveying industry thanks to low costs and ease of use. Although these UAVs have relatively high-resolution imaging systems, there exists a near exponential relationship between the ground sampling distance (GSD) and the number of images required - which is a function of flight altitude. To tackle this, we use a generative network based super-resolution approach to increase the GSD of images which effectively reduces flight time. In this paper we test the efficiency and efficacy of this approach using two multimedia super-resolution implementations. We also provide quantitative results comparing the two using various image processing metrics.