scholarly journals AN EFFICIENT REPRESENTATION OF 3D BUILDINGS: APPLICATION TO THE EVALUATION OF CITY MODELS

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 329-336
Author(s):  
O. Ennafii ◽  
A. Le Bris ◽  
F. Lafarge ◽  
C. Mallet
Keyword(s):  
Evaluation Process ◽  
Point Clouds ◽  
Classification Problem ◽  
Boundary Representation ◽  
3D Point Clouds ◽  
Learning Tasks ◽  
Building Models ◽  
Urban Models ◽  
Efficient Representation ◽  
Building Level

Abstract. City modeling consists in building a semantic generalized model of the surface of urban objects. These could be seen as a special case of Boundary representation surfaces. Most modeling methods focus on 3D buildings with Very High Resolution overhead data (images and/or 3D point clouds). The literature abundantly addresses 3D mesh processing but frequently ignores the analysis of such models. This requires an efficient representation of 3D buildings. In particular, for them to be used in supervised learning tasks, such a representation should be scalable and transferable to various environments as only a few reference training instances would be available. In this paper, we propose two solutions that take into account the specificity of 3D urban models. They are based on graph kernels and Scattering Network. They are here evaluated in the challenging framework of quality evaluation of building models. The latter is formulated as a supervised multilabel classification problem, where error labels are predicted at building level. The experiments show for both feature extraction strategy strong and complementary results (F-score > 74% for most labels). Transferability of the classification is also examined in order to assess the scalability of the evaluation process yielding very encouraging scores (F-score > 86% for most labels).

scholarly journals Seismic Damage Semantics on Post-Earthquake LOD3 Building Models Generated by UAS

2021 ◽  
Vol 10 (5) ◽  
pp. 345
Author(s):  
Konstantinos Chaidas ◽  
George Tataris ◽  
Nikolaos Soulakellis
Keyword(s):  
Point Clouds ◽  
Recovery Phase ◽  
Seismic Damage ◽  
Unmanned Aircraft ◽  
Earthquake Scenario ◽  
Geography Markup Language ◽  
3D Point Clouds ◽  
Building Models ◽  
Building Walls ◽  
Oblique Images

In a post-earthquake scenario, the semantic enrichment of 3D building models with seismic damage is crucial from the perspective of disaster management. This paper aims to present the methodology and the results for the Level of Detail 3 (LOD3) building modelling (after an earthquake) with the enrichment of the semantics of the seismic damage based on the European Macroseismic Scale (EMS-98). The study area is the Vrisa traditional settlement on the island of Lesvos, Greece, which was affected by a devastating earthquake of Mw = 6.3 on 12 June 2017. The applied methodology consists of the following steps: (a) unmanned aircraft systems (UAS) nadir and oblique images are acquired and photogrammetrically processed for 3D point cloud generation, (b) 3D building models are created based on 3D point clouds and (c) 3D building models are transformed into a LOD3 City Geography Markup Language (CityGML) standard with enriched semantics of the related seismic damage of every part of the building (walls, roof, etc.). The results show that in following this methodology, CityGML LOD3 models can be generated and enriched with buildings’ seismic damage. These models can assist in the decision-making process during the recovery phase of a settlement as well as be the basis for its monitoring over time. Finally, these models can contribute to the estimation of the reconstruction cost of the buildings.

scholarly journals AUTOMATIC GENERATION OF BUILDING MODELS WITH LEVELS OF DETAIL 1-3

2016 ◽  
Vol XLI-B3 ◽  
pp. 649-654 ◽  
Author(s):  
W. Nguatem ◽  
M. Drauschke ◽  
H. Mayer
Keyword(s):  
Model Selection ◽  
Point Clouds ◽  
Automatic Generation ◽  
Stochastic Method ◽  
Depth Maps ◽  
Levels Of Detail ◽  
3D Point Clouds ◽  
Building Models ◽  
Global Matching

We present a workflow for the automatic generation of building models with levels of detail (LOD) 1 to 3 according to the CityGML standard (Gröger et al., 2012). We start with orienting unsorted image sets employing (Mayer et al., 2012), we compute depth maps using semi-global matching (SGM) (Hirschmüller, 2008), and fuse these depth maps to reconstruct dense 3D point clouds (Kuhn et al., 2014). Based on planes segmented from these point clouds, we have developed a stochastic method for roof model selection (Nguatem et al., 2013) and window model selection (Nguatem et al., 2014). We demonstrate our workflow up to the export into CityGML.

Use of topographic LiDAR point clouds for building reconstruction

2021 ◽  
Author(s):  
Yipeng Yuan
Keyword(s):  
Large Scale ◽  
Three Dimensional ◽  
Point Clouds ◽  
Building Roof ◽  
Building Model ◽  
Building Models ◽  
Urban Models ◽  
Elevation Data ◽  
3D Building Model ◽  
Building Reconstruction

Demand for three-dimensional (3D) urban models keeps growing in various civil and military applications. Topographic LiDAR systems are capable of acquiring elevation data directly over terrain features. However, the task of creating a large-scale virtual environment still remains a time-consuming and manual work. In this thesis a method for 3D building reconstruction, consisting of building roof detection, roof outline extraction and regularization, and 3D building model generation, directly from LiDAR point clouds is developed. In the proposed approach, a new algorithm called Gaussian Markov Random Field (GMRF) and Markov Chain Monte Carlo (MCMC) is used to segment point clouds for building roof detection. The modified convex hull (MCH) algorithm is used for the extraction of roof outlines followed by the regularization of the extracted outlines using the modified hierarchical regularization algorithm. Finally, 3D building models are generated in an ArcGIS environment. The results obtained demonstrate the effectiveness and satisfactory accuracy of the developed method.

scholarly journals BUILDING FEATURES RECOGNITION FROM UNCERTAIN 3D LIDAR POINT CLOUDS: A SEMANTIC APPROACH

2020 ◽  
Vol XLIII-B4-2020 ◽  
pp. 89-96
Author(s):  
X.-F. Xing ◽  
M. A. Mostafavi
Keyword(s):  
Point Cloud ◽  
Evaluation Process ◽  
Point Clouds ◽  
Semantic Approach ◽  
Semantic Reasoning ◽  
Knowledge Based ◽  
3D Point Clouds ◽  
Building Components ◽  
3D Lidar

Abstract. LiDAR technology allows rapid observation of high-resolution and precise 3D point clouds for diverse applications in urban and natural areas. However, uneven density and incomplete point clouds make LiDAR data processing more challenging for the extraction of semantic information on objects and their components. In this paper, we propose a knowledge based semantic reasoning solution for the recognition of building components (e.g. roofs) from segmentation results in the presence of uncertainties in LiDAR point clouds. The proposed solution uses a semantic reasoning approach as well as a similarity evaluation process for object recognition. We apply the proposed method to recognize buildings’ roof styles from a point cloud with uncertainty as a case study.

scholarly journals GRAMMAR-SUPPORTED 3D INDOOR RECONSTRUCTION FROM POINT CLOUDS FOR “AS-BUILT” BIM

2015 ◽  
Vol II-3/W4 ◽  
pp. 17-24 ◽  
Author(s):  
S. Becker ◽  
M. Peter ◽  
D. Fritsch
Keyword(s):  
Point Clouds ◽  
Observation Data ◽  
Reconstruction Process ◽  
Building Model ◽  
3D Point Clouds ◽  
Building Models ◽  
Seamless Transition ◽  
Floor Plans ◽  
Knowledge Content ◽  
Realistic Geometries

The paper presents a grammar-based approach for the robust automatic reconstruction of 3D interiors from raw point clouds. The core of the approach is a 3D indoor grammar which is an extension of our previously published grammar concept for the modeling of 2D floor plans. The grammar allows for the modeling of buildings whose horizontal, continuous floors are traversed by hallways providing access to the rooms as it is the case for most office buildings or public buildings like schools, hospitals or hotels. The grammar is designed in such way that it can be embedded in an iterative automatic learning process providing a seamless transition from LOD3 to LOD4 building models. Starting from an initial low-level grammar, automatically derived from the window representations of an available LOD3 building model, hypotheses about indoor geometries can be generated. The hypothesized indoor geometries are checked against observation data - here 3D point clouds - collected in the interior of the building. The verified and accepted geometries form the basis for an automatic update of the initial grammar. By this, the knowledge content of the initial grammar is enriched, leading to a grammar with increased quality. This higher-level grammar can then be applied to predict realistic geometries to building parts where only sparse observation data are available. Thus, our approach allows for the robust generation of complete 3D indoor models whose quality can be improved continuously as soon as new observation data are fed into the grammar-based reconstruction process. The feasibility of our approach is demonstrated based on a real-world example.

scholarly journals EXTRACTING SEMANTICALLY ANNOTATED 3D BUILDING MODELS WITH TEXTURES FROM OBLIQUE AERIAL IMAGERY

2015 ◽  
Vol XL-3/W2 ◽  
pp. 53-58 ◽  
Author(s):  
D. Frommholz ◽  
M. Linkiewicz ◽  
H. Meissner ◽  
D. Dahlke ◽  
A. Poznanska
Keyword(s):  
High Resolution ◽  
Software Package ◽  
Point Clouds ◽  
Aerial Imagery ◽  
Commercial Software ◽  
Camera System ◽  
3D Point Clouds ◽  
Building Models ◽  
Commercial Software Package

This paper proposes a method for the reconstruction of city buildings with automatically derived textures that can be directly used for façade element classification. Oblique and nadir aerial imagery recorded by a multi-head camera system is transformed into dense 3D point clouds and evaluated statistically in order to extract the hull of the structures. For the resulting wall, roof and ground surfaces high-resolution polygonal texture patches are calculated and compactly arranged in a texture atlas without resampling. The façade textures subsequently get analyzed by a commercial software package to detect possible windows whose contours are projected into the original oriented source images and sparsely ray-casted to obtain their 3D world coordinates. With the windows being reintegrated into the previously extracted hull the final building models are stored as semantically annotated CityGML ”LOD-2.5” objects.

scholarly journals PROBABILITY DENSITY BASED CLASSIFICATION AND RECONSTRUCTION OF ROOF STRUCTURES FROM 3D POINT CLOUDS

2019 ◽  
Vol XLII-4/W16 ◽  
pp. 177-184
Author(s):  
Y. Dehbi ◽  
S. Koppers ◽  
L. Plümer
Keyword(s):  
Probability Density ◽  
Real Data ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Support Vector ◽  
Model Based ◽  
3D Point Clouds ◽  
Building Models ◽  
Starting Point ◽  
Vector Machines

Abstract. 3D building models including roofs are a key prerequisite in many fields of applications such as the estimation of solar suitability of rooftops. The accurate reconstruction of roofs with dormers is sometimes challenging. Without careful separation of the dormer points from the points on the roof surface, the estimation of the roof areas is distorted in a most characteristic way, which then let the dormer points appear as white noise. The characteristic distortion of the density distribution of the defects by dormers in comparison to the expected normal distribution is the starting point of our method. We propose a hierarchical method which improves roof reconstruction from LiDAR point clouds in a model-based manner separating dormer points from roof points using classification methods. The key idea is to exploit probability density functions (PDFs) to reveal roof properties and design skilful features for a supervised learning method using support vector machines (SVMs). Properties of the PDFs of measures such as residuals of model-based estimated roof models are used among others. A clustering step leads to a semantic segmentation of the point cloud enabling subsequent reconstruction. The approach is tested based on real data as well as simulated point clouds. The latter allow for experiments for various roof and dormer types with different parameters using an implemented simulation toolbox which generates virtual buildings and synthetic point clouds.

scholarly journals Reconstruction of Complex Roof Semantic Structures from 3D Point Clouds Using Local Convexity and Consistency

2021 ◽  
Vol 13 (10) ◽  
pp. 1946
Author(s):  
Pingbo Hu ◽  
Yiming Miao ◽  
Miaole Hou
Keyword(s):  
State Of The Art ◽  
Three Dimensional ◽  
Reconstruction Algorithm ◽  
Point Clouds ◽  
Urban Environments ◽  
Automated Modeling ◽  
3D Point Clouds ◽  
Building Models ◽  
Complex Building ◽  
Topology Information

Three-dimensional (3D) building models are closely related to human activities in urban environments. Due to the variations in building styles and complexity in roof structures, automatically reconstructing 3D buildings with semantics and topology information still faces big challenges. In this paper, we present an automated modeling approach that can semantically decompose and reconstruct the complex building light detection and ranging (LiDAR) point clouds into simple parametric structures, and each generated structure is an unambiguous roof semantic unit without overlapping planar primitive. The proposed method starts by extracting roof planes using a multi-label energy minimization solution, followed by constructing a roof connection graph associated with proximity, similarity, and consistency attributes. Furthermore, a progressive decomposition and reconstruction algorithm is introduced to generate explicit semantic subparts and hierarchical representation of an isolated building. The proposed approach is performed on two various datasets and compared with the state-of-the-art reconstruction techniques. The experimental modeling results, including the assessment using the International Society for Photogrammetry and Remote Sensing (ISPRS) benchmark LiDAR datasets, demonstrate that the proposed modeling method can efficiently decompose complex building models into interpretable semantic structures.

scholarly journals Learning Rotations

2021 ◽  
Author(s):  
Alberto Pepe ◽  
Joan Lasenby ◽  
Pablo Chacón
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Point Clouds ◽  
Inverse Kinematic ◽  
Inverse Kinematic Problem ◽  
3D Point Clouds ◽  
Learning Tasks ◽  
Regression Error ◽  
Robustness To Noise ◽  
Gimbal Lock

Many problems in computer vision today are solved via deep learning. Tasks like pose estimation from images, pose estimation from point clouds or structure from motion can all be formulated as a regression on rotations. However, there is no unique way of parametrizing rotations mathematically: matrices, quaternions, axis-angle representation or Euler angles are all commonly used in the field. Some of them, however, present intrinsic limitations, including discontinuities, gimbal lock or antipodal symmetry. These limitations may make the learning of rotations via neural networks a challenging problem, potentially introducing large errors. Following recent literature, we propose three case studies: a sanity check, a pose estimation from 3D point clouds and an inverse kinematic problem. We do so by employing a full geometric algebra (GA) description of rotations. We compare the GA formulation with a 6D continuous representation previously presented in the literature in terms of regression error and reconstruction accuracy. We empirically demonstrate that parametrizing rotations as bivectors outperforms the 6D representation. The GA approach overcomes the continuity issue of representations as the 6D representation does, but it also needs fewer parameters to be learned and offers an enhanced robustness to noise. GA hence provides a broader framework for describing rotations in a simple and compact way that is suitable for regression tasks via deep learning, showing high regression accuracy and good generalizability in realistic high-noise scenarios.

Sign in / Sign up

Export Citation Format

Share Document