Abstract
The digital elevation model (DEM) generates a digital simulation of ground terrain in a certain range with the usage of 3D point cloud data. It is an important source of spatial modeling information. Due to various reasons, however, the generated DEM has data holes. Based on the algorithm of deep learning, this paper aims to train a deep generation model (DGM) to complete the DEM void filling task. A certain amount of DEM data and a randomly generated mask are taken as network inputs, along which the reconstruction loss and generative adversarial network (GAN) loss are used to assist network training, so as to perceive the overall known elevation information, in combination with the contextual attention layer, and generate data with reliability to fill the void areas. The experimental results have managed to show that this method has good feature expression and reconstruction accuracy in DEM void filling, which has been proven to be better than that illustrated by the traditional interpolation method.
Highlights
The digital elevation model (DEM) has wide applications and significant value in surveying and mapping [1], hydrology [2] and earth science [3]
The common way to obtain DEM data is by low-altitude photogrammetry, in which the point cloud data is obtained by dense matching
USGS DEM mainly has two types of grid forms; one is a Mercator projection (UTM) grid, and the other is a geographical coordinate grid divided into seconds
Summary
The digital elevation model (DEM) has wide applications and significant value in surveying and mapping [1], hydrology [2] and earth science [3]. The common way to obtain DEM data is by low-altitude photogrammetry, in which the point cloud data is obtained by dense matching. By covering a large scope of areas, this method can provide image texture information so as to basically meet the requirement of DEM construction [4]. Due to a series of reasons, such as the dead angle of aerial photography, matching deviation and insufficient point position, the DEM constructed in most circumstances has holes of different sizes and shapes. The DEM data with holes hinders the acquisition of various terrain and geomorphic structure information, which would further make it difficult to provide and couple geospatial information well. In the process of actual production, if the constructed high spatial resolution DEM has voids, it will produce an incomplete expression of the morphological characteristics of erosion trenches [5], while the missing data would cause erroneous estimation of the material balance accuracy of mountain glaciers [6] and difficulties in eliminating topographic cracks [7]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
