Digital Terrain Models from Airborne Laser Scanning for the Automatic Extraction of Natural and Anthropogenic Linear Structures

2011 ◽  
pp. 475-488 ◽  
Author(s):  
Rutzinger Martin ◽  
Höfle Bernhard ◽  
Vetter Michael ◽  
Pfeifer Norbert
Keyword(s):  
Laser Scanning ◽  
Airborne Laser Scanning ◽  
Automatic Extraction ◽  
Linear Structures ◽  
Digital Terrain Models ◽  
Digital Terrain ◽  
Terrain Models ◽  
Airborne Laser

scholarly journals Airborne laser scanning and usefulness for hydrological models

2005 ◽  
Vol 5 ◽  
pp. 57-63 ◽  
Author(s):  
M. Hollaus ◽  
W. Wagner ◽  
K. Kraus
Keyword(s):  
Laser Scanning ◽  
Laser Scanner ◽  
Airborne Laser Scanning ◽  
Scanner Data ◽  
Digital Terrain Models ◽  
Mountainous Regions ◽  
Digital Terrain ◽  
Terrain Models ◽  
Airborne Laser ◽  
Land Cover Maps

Abstract. Digital terrain models form the basis for distributed hydrologic models as well as for two-dimensional hydraulic river flood models. The technique used for generating high accuracy digital terrain models has shifted from stereoscopic aerial-photography to airborne laser scanning during the last years. Since the disastrous floods 2002 in Austria, large airborne laser-scanning flight campaigns have been carried out for several river basins. Additionally to the topographic information, laser scanner data offer also the possibility to estimate object heights (vegetation, buildings). Detailed land cover maps can be derived in conjunction with the complementary information provided by high-resolution colour-infrared orthophotos. As already shown in several studies, the potential of airborne laser scanning to provide data for hydrologic/hydraulic applications is high. These studies were mostly constraint to small test sites. To overcome this spatial limitation, the current paper summarises the experiences to process airborne laser scanner data for large mountainous regions, thereby demonstrating the applicability of this technique in real-world hydrological applications.

Interpreting cultural remains in airborne laser scanning generated digital terrain models: effects of size and shape on detection success rates

2013 ◽  
Vol 40 (12) ◽  
pp. 4688-4700 ◽  
Author(s):  
Ole Risbøl ◽  
Ole Martin Bollandsås ◽  
Anneli Nesbakken ◽  
Hans Ole Ørka ◽  
Erik Næsset ◽  
...  
Keyword(s):  
Laser Scanning ◽  
Airborne Laser Scanning ◽  
Success Rates ◽  
Digital Terrain Models ◽  
Size And Shape ◽  
Digital Terrain ◽  
Terrain Models ◽  
Airborne Laser

scholarly journals Accuracy Assessment of Point Clouds from LiDAR and Dense Image Matching Acquired Using the UAV Platform for DTM Creation

2018 ◽  
Vol 7 (9) ◽  
pp. 342 ◽  
Author(s):  
Adam Salach ◽  
Krzysztof Bakuła ◽  
Magdalena Pilarska ◽  
Wojciech Ostrowski ◽  
Konrad Górski ◽  
...  
Keyword(s):  
Land Cover ◽  
Laser Scanning ◽  
Point Clouds ◽  
Data Sources ◽  
Digital Terrain Models ◽  
Vegetation Height ◽  
Digital Terrain ◽  
Terrain Models ◽  
Airborne Laser ◽  
Vertical Accuracy

In this paper, the results of an experiment about the vertical accuracy of generated digital terrain models were assessed. The created models were based on two techniques: LiDAR and photogrammetry. The data were acquired using an ultralight laser scanner, which was dedicated to Unmanned Aerial Vehicle (UAV) platforms that provide very dense point clouds (180 points per square meter), and an RGB digital camera that collects data at very high resolution (a ground sampling distance of 2 cm). The vertical error of the digital terrain models (DTMs) was evaluated based on the surveying data measured in the field and compared to airborne laser scanning collected with a manned plane. The data were acquired in summer during a corridor flight mission over levees and their surroundings, where various types of land cover were observed. The experiment results showed unequivocally, that the terrain models obtained using LiDAR technology were more accurate. An attempt to assess the accuracy and possibilities of penetration of the point cloud from the image-based approach, whilst referring to various types of land cover, was conducted based on Real Time Kinematic Global Navigation Satellite System (GNSS-RTK) measurements and was compared to archival airborne laser scanning data. The vertical accuracy of DTM was evaluated for uncovered and vegetation areas separately, providing information about the influence of the vegetation height on the results of the bare ground extraction and DTM generation. In uncovered and low vegetation areas (0–20 cm), the vertical accuracies of digital terrain models generated from different data sources were quite similar: for the UAV Laser Scanning (ULS) data, the RMSE was 0.11 m, and for the image-based data collected using the UAV platform, it was 0.14 m, whereas for medium vegetation (higher than 60 cm), the RMSE from these two data sources were 0.11 m and 0.36 m, respectively. A decrease in the accuracy of 0.10 m, for every 20 cm of vegetation height, was observed for photogrammetric data; and such a dependency was not noticed in the case of models created from the ULS data.

scholarly journals Extraction of linear structures from digital terrain models using deep learning

2021 ◽  
Vol 2 ◽  
pp. 1-14
Author(s):  
Ramish Satari ◽  
Bashir Kazimi ◽  
Monika Sester
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Laser Scanning ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Linear Structures ◽  
Digital Terrain Models ◽  
Deep Convolutional Neural Networks ◽  
Digital Terrain ◽  
Terrain Models

Abstract. This paper explores the role deep convolutional neural networks play in automated extraction of linear structures using semantic segmentation techniques in Digital Terrain Models (DTMs). DTM is a regularly gridded raster created from laser scanning point clouds and represents elevations of the bare earth surface with respect to a reference. Recent advances in Deep Learning (DL) have made it possible to explore the use of semantic segmentation for detection of terrain structures in DTMs. This research examines two novel and practical deep convolutional neural network architectures i.e. an encoder-decoder network named as SegNet and the recent state-of-the-art high-resolution network (HRNet). This paper initially focuses on the pixel-wise binary classification in order to validate the applicability of the proposed approaches. The networks are trained to distinguish between points belonging to linear structures and those belonging to background. In the second step, multi-class segmentation is carried out on the same DTM dataset. The model is trained to not only detect a linear feature, but also to categorize it as one of the classes: hollow ways, roads, forest paths, historical paths, and streams. Results of the experiment in addition to the quantitative and qualitative analysis show the applicability of deep neural networks for detection of terrain structures in DTMs. From the deep learning models utilized, HRNet gives better results.

Sign in / Sign up

Export Citation Format

Share Document