Abstract
High-resolution digital elevation models (DEMs) play a critical role in geospatial databases, which can be applied to many terrain-related studies such as facility siting, hydrological analysis, and urban design. However, due to the limitation of precision of equipment, there are big gaps to collect high-resolution DEM data. A practical idea is to recover high-resolution DEMs from easily obtained low-resolution DEMs, and this process is termed DEM super-resolution (SR). However, traditional DEM SR methods (e.g., bicubic interpolation) tend to over-smooth high-frequency regions on account of the operation of averaging local variations. With the recent development of machine learning, image SR methods have made great progress. Nevertheless, due to the complexity of terrain characters (e.g., peak and valley) and the huge difference between elevation field and image RGB (Red, Green, and Blue) value field, there are few works that apply image SR methods to the task of DEM SR. Therefore, this paper investigates the question of whether the state-of-the-art image SR methods are appropriate for DEM SR. More specifically, the traditional interpolation method and three excellent SR methods based on neural networks are chosen for comparison. Experimental results suggest that SRGAN (Super-Resolution with Generative Adversarial Network) presents the best performance on accuracy evaluation over a series of DEM SR experiments.
Highlights
As one of the most important digital representations of terrain, digital elevation models (DEMs) record spatial elevation information in a regular raster form [1]
Experimental results suggest that SRGAN (Super-Resolution with Generative Adversarial Network) presents the best performance on accuracy evaluation over a series of DEM SR experiments
To investigate the effectiveness of the selected methods on DEM SR (SRGAN, ESRGAN, and CEDGAN), a dataset of digital elevation models (DEMs) with complex terrain features is used in this paper, which was acquired from the USGS (United States Geological Survey)
Summary
As one of the most important digital representations of terrain, DEMs record spatial elevation information in a regular raster form [1]. Through visualizing fluctuating characters of terrain surfaces, DEMs can be widely applied in the domains including facility siting, hydrological analysis, and urban design [2,3,4]. With the rapid development of measuring equipment, DEM data can be generated from various sources, which accelerate its universality in landform analysis applications [5]. Despite the wide usage of SAR data, the limitation of equipment precision can still result in systematic errors that reduce the resolutions of DEM products. The inadequate spatial resolution of DEM data restricts its usage in terrain-related analyses [7,8]. The most direct solution to obtain high-resolution DEM is to improve the precision of measuring equipment, but this process is difficult, costly, and time-consuming. Generating high-resolution DEMs without extra cost becomes a key concern of researchers from various fields [11,12]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
