Super Resolution based on Deep Learning Technique for constructing Digital Elevation Model

2016 ◽  
Author(s):  
SungHyun Moon ◽  
Han-Lim Choi
Keyword(s):  
Deep Learning ◽  
Digital Elevation Model ◽  
Super Resolution ◽  
Digital Elevation ◽  
Learning Technique ◽  
Elevation Model

scholarly journals RSPCN: Super-Resolution of Digital Elevation Model Based on Recursive Sub-Pixel Convolutional Neural Networks

2021 ◽  
Vol 10 (8) ◽  
pp. 501
Author(s):  
Ruichen Zhang ◽  
Shaofeng Bian ◽  
Houpu Li
Keyword(s):  
Neural Networks ◽  
Digital Elevation Model ◽  
Convolutional Neural Networks ◽  
Adaptive Learning ◽  
Nearest Neighbor ◽  
Super Resolution ◽  
Recursion Theory ◽  
Research Issues ◽  
Digital Elevation ◽  
Elevation Model

The digital elevation model (DEM) is known as one kind of the most significant fundamental geographical data models. The theory, method and application of DEM are hot research issues in geography, especially in geomorphology, hydrology, soil and other related fields. In this paper, we improve the efficient sub-pixel convolutional neural networks (ESPCN) and propose recursive sub-pixel convolutional neural networks (RSPCN) to generate higher-resolution DEMs (HRDEMs) from low-resolution DEMs (LRDEMs). Firstly, the structure of RSPCN is described in detail based on recursion theory. This paper explores the effects of different training datasets, with the self-adaptive learning rate Adam algorithm optimizing the model. Furthermore, the adding-“zero” boundary method is introduced into the RSPCN algorithm as a data preprocessing method, which improves the RSPCN method’s accuracy and convergence. Extensive experiments are conducted to train the method till optimality. Finally, comparisons are made with other traditional interpolation methods, such as bicubic, nearest-neighbor and bilinear methods. The results show that our method has obvious improvements in both accuracy and robustness and further illustrate the feasibility of deep learning methods in the DEM data processing area.

scholarly journals Super-resolution reconstruction of a digital elevation model based on a deep residual network

2020 ◽  
Vol 12 (1) ◽  
pp. 1369-1382
Author(s):  
Donglai Jiao ◽  
Dajiang Wang ◽  
Haiyang Lv ◽  
Yang Peng
Keyword(s):  
Digital Elevation Model ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Feature Mapping ◽  
Residual Network ◽  
Network Layers ◽  
Development Cycle ◽  
Digital Elevation ◽  
Elevation Model ◽  
Better Than

AbstractThe digital elevation model (DEM) is an important basic data tool applied in geoscience applications. Because of its high cost and long development cycle of enhancing hardware performance, designing the related models and algorithms to improve the resolution of DEM is of considerable significance. At present, there is little research on DEM super-resolution based on deep learning, and the results of the reconstructed DEMs obtained by existing methods are inaccurate. Therefore, deepening of the network layers is utilized to improve the accuracy of a reconstructed DEM. This paper designs a neutral network model with 30 convolutional layers to learn the feature mapping relationship between a low- and high-resolution DEM. To avoid the problem of network degradation caused by increasing the number of convolutional layers, residual learning is introduced to accelerate the convergence speed of the model, thereby preferably realizing the DEM super-resolution process. The results show that DEM super-resolution based on a deep residual network is better than that obtained using a neural network with fewer convolutional layers, and the reconstructed result of the DEM based on a deep residual network is remarkably improved in terms of the peak signal to noise ratio and visual effect.

STUDY OF THE LANDSLIDE MORPHOLOGY BASED ON GNSS DATA AND AIRBORNE SOUNDING (ON THE EXAMPLE OF A SECTION OF THE PROTVA RIVER VALLEY)

2018 ◽  
Vol 12 (5-6) ◽  
pp. 50-57 ◽  
Author(s):  
I. S. Voskresensky ◽  
A. A. Suchilin ◽  
L. A. Ushakova ◽  
V. M. Shaforostov ◽  
A. L. Entin ◽  
...  
Keyword(s):  
Digital Elevation Model ◽  
Geodetic Network ◽  
Aerial Survey ◽  
River Valley ◽  
Ease Of Use ◽  
Digital Elevation ◽  
Loose Deposits ◽  
Positioning Method ◽  
Landslide Body ◽  
Elevation Model

To use unmanned aerial vehicles (UAVs) for obtaining digital elevation models (DEM) and digital terrain models (DTM) is currently actively practiced in scientific and practical purposes. This technology has many advantages: efficiency, ease of use, and the possibility of application on relatively small area. This allows us to perform qualitative and quantitative studies of the progress of dangerous relief-forming processes and to assess their consequences quickly. In this paper, we describe the process of obtaining a digital elevation model (DEM) of the relief of the slope located on the bank of the Protva River (Satino training site of the Faculty of Geography, Lomonosov Moscow State University). To obtain the digital elevation model, we created a temporary geodetic network. The coordinates of the points were measured by the satellite positioning method using a highprecision mobile complex. The aerial survey was carried out using an unmanned aerial vehicle from a low altitude (about 40–45 m). The processing of survey materials was performed via automatic photogrammetry (Structure-from-Motion method), and the digital elevation model of the landslide surface on the Protva River valley section was created. Remote sensing was supplemented by studying archival materials of aerial photography, as well as field survey conducted immediately after the landslide. The total amount of research results made it possible to establish the causes and character of the landslide process on the study site. According to the geomorphological conditions of formation, the landslide refers to a variety of landslideslides, which are formed when water is saturated with loose deposits. The landslide body was formed with the "collapse" of the blocks of turf and deluvial loams and their "destruction" as they shifted and accumulated at the foot of the slope.

Sign in / Sign up

Export Citation Format

Share Document