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.

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 ENHANCING THE RESOLUTION OF URBAN DIGITAL TERRAIN MODELS USING MOBILE MAPPING SYSTEMS

2018 ◽  
Vol IV-4/W6 ◽  
pp. 11-18
Author(s):  
Y. Feng ◽  
C. Brenner ◽  
M. Sester
Keyword(s):  
Urban Areas ◽  
Laser Scanning ◽  
Overland Flow ◽  
Point Clouds ◽  
Digital Terrain Models ◽  
Mobile Mapping ◽  
Flow Modelling ◽  
Digital Terrain ◽  
Terrain Models ◽  
Mapping Techniques

<p><strong>Abstract.</strong> Digital Terrain Models (DTMs) are essential surveying products for terrain based analyses, especially for overland flow modelling. Nowadays, many high resolution DTM products are generated by Airborne Laser Scanning (ALS). However, DTMs with even higher resolution are of great interest for a more precise overland flow modelling in urban areas. With the help of mobile mapping techniques, we can obtain much denser measurements of the ground in the vicinity of roads. In this research, a study area in Hannover, Germany was measured by a mobile mapping system. Point clouds from 485 scan strips were aligned and a DTM was extracted. In order to achieve a product with completeness, this mobile mapping produced DTM was then merged and adapted with a DTM product with 0.5<span class="thinspace"></span>m resolution from a mapping agency. Systematic evaluations have been conducted with respect to the height accuracy of the DTM products. The results show that the final DTM product achieved a higher resolution (0.1<span class="thinspace"></span>m) near the roads while essentially maintaining its height accuracy.</p>

scholarly journals Comparing Machine and Deep Learning Methods for Large 3D Heritage Semantic Segmentation

2020 ◽  
Vol 9 (9) ◽  
pp. 535
Author(s):  
Francesca Matrone ◽  
Eleonora Grilli ◽  
Massimo Martini ◽  
Marina Paolanti ◽  
Roberto Pierdicca ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cultural Heritage ◽  
Laser Scanning ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Classification Algorithms ◽  
Learning Methods ◽  
3D Point Clouds ◽  
The Subject

In recent years semantic segmentation of 3D point clouds has been an argument that involves different fields of application. Cultural heritage scenarios have become the subject of this study mainly thanks to the development of photogrammetry and laser scanning techniques. Classification algorithms based on machine and deep learning methods allow to process huge amounts of data as 3D point clouds. In this context, the aim of this paper is to make a comparison between machine and deep learning methods for large 3D cultural heritage classification. Then, considering the best performances of both techniques, it proposes an architecture named DGCNN-Mod+3Dfeat that combines the positive aspects and advantages of these two methodologies for semantic segmentation of cultural heritage point clouds. To demonstrate the validity of our idea, several experiments from the ArCH benchmark are reported and commented.

scholarly journals FILTERING PHOTOGRAMMETRIC POINT CLOUDS USING STANDARD LIDAR FILTERS TOWARDS DTM GENERATION

2018 ◽  
Vol IV-2 ◽  
pp. 319-326 ◽  
Author(s):  
Z. Zhang ◽  
M. Gerke ◽  
G. Vosselman ◽  
M. Y. Yang
Keyword(s):  
Laser Scanning ◽  
Type I Error ◽  
Research Question ◽  
Random Noise ◽  
Point Clouds ◽  
Type I ◽  
Low Contrast ◽  
Digital Terrain ◽  
Terrain Models ◽  
Dense Matching

Digital Terrain Models (DTMs) can be generated from point clouds acquired by laser scanning or photogrammetric dense matching. During the last two decades, much effort has been paid to developing robust filtering algorithms for the airborne laser scanning (ALS) data. With the point cloud quality from dense image matching (DIM) getting better and better, the research question that arises is whether those standard Lidar filters can be used to filter photogrammetric point clouds as well. Experiments are implemented to filter two dense matching point clouds with different noise levels. Results show that the standard Lidar filter is robust to random noise. However, artefacts and blunders in the DIM points often appear due to low contrast or poor texture in the images. Filtering will be erroneous in these locations. Filtering the DIM points pre-processed by a ranking filter will bring higher Type II error (i.e. non-ground points actually labelled as ground points) but much lower Type I error (i.e. bare ground points labelled as non-ground points). Finally, the potential DTM accuracy that can be achieved by DIM points is evaluated. Two DIM point clouds derived by Pix4Dmapper and SURE are compared. On grassland dense matching generates points higher than the true terrain surface, which will result in incorrectly elevated DTMs. The application of the ranking filter leads to a reduced bias in the DTM height, but a slightly increased noise level.

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.

Algorithm for eliminating redundant air laser scanning data for constructing digital terrain models

2017 ◽  
Vol 927 (9) ◽  
pp. 50-54
Author(s):  
A.A. Kochneva ◽  
S.B. Kryltcov
Keyword(s):  
Computational Complexity ◽  
Laser Scanning ◽  
Model Building ◽  
Digital Terrain Models ◽  
Software Products ◽  
Digital Terrain ◽  
Terrain Models ◽  
The Earth ◽  
Algorithm Operation

The wide use of air laser scanning for the building of digital terrain models in Russia has been used for more than 20 years. To process the results of air laser scanning, it is necessary to classify the points of laser reflections. Classification of laser reflection points is carried out by international commercial software products, often using algorithms of rarefaction of the “Earth” class data, which does not consider the features of the relief shape. In the paper, it has been proposed a proprietary algorithm for interpolating laser scanning data, which allows the removal of redundant points of “Earth” class laser reflections with a primarily reduction in the detail of the flat terrain data. A distinctive feature of the proposed solution is its low computational complexity. This allows the algorithm to work effectively with large arrays of data, obtained during air laser scanning. The paper presents a detailed step-by-step description of the algorithm operation, as well as the results of the digital relief model building based on a cloud of laser reflection points of the Earth class, processed using the proposed algorithm.

Sign in / Sign up

Export Citation Format

Share Document