This paper discusses the reconstruction of LoD2 building models from 2D and 3D data for large-scale urban environments. Traditional methods involve the use of LiDAR point clouds, but due to high costs and long intervals associated with acquiring such data for rapidly developing areas, researchers have started exploring the use of point clouds generated from (oblique) aerial images. However, using such point clouds for traditional plane detection-based methods can result in significant errors and introduce noise into the reconstructed building models. To address this, this paper presents a method for extracting rooflines from true orthophotos using line detection for the reconstruction of building models at the LoD2 level. The approach is able to extract relatively complete rooflines without the need for pre-labeled training data or pre-trained models. These lines can directly be used in the LoD2 building model reconstruction process. The method is superior to existing plane detection-based methods and state-of-the-art deep learning methods in terms of the accuracy and completeness of the reconstructed building. Our source code is available at https://github.com/tudelft3d/Roofline-extraction-from-orthophotos.@en

With the rapid advancement of 3D sensing technologies, obtaining 3D shape information of objects has become increasingly convenient. Lidar technology, with its capability to accurately capture the 3D information of objects at long distances, has been widely applied in the collection of 3D data in urban scenes. However, the collected point cloud data often exhibit incompleteness due to factors such as occlusion, signal absorption, and specular reflection. This paper explores the application of point cloud completion technologies in processing these incomplete data and establishes a new real-world benchmark Building-PCC dataset, to evaluate the performance of existing deep learning methods in the task of urban building point cloud completion. Through a comprehensive evaluation of different methods, we analyze the key challenges faced in building point cloud completion, aiming to promote innovation in the field of 3D geoinformation applications. Our source code is available at https://github.com/ tudelft3d/Building-PCC-Building-Point-Cloud-Completion-Benchmarks.git@en

Reconstructing urban scenarios for computational fluid dynamics simulations typically requires significant manual effort, especially when higher geometrical details are required. To address this issue, we present a workflow to automatically reconstruct buildings in three levels of detail (LoDs): LoD1.2, LoD1.3, and LoD2.2, tailored to urban microscale simulations. The workflow uses a combination of building footprints and a point cloud to segment roof planes, create partitions, optimise planes, and finally assemble roof planes into 3D building models. Reconstructed buildings are seamlessly integrated into the terrain together with different surface layers such as water, low vegetation, and paved surfaces. Apart from three general LoDs, building footprints can be simplified as a part of the 2D generalisation; additionally, smaller surfaces such as chimneys and ventilation shafts can be removed using a graph-cut optimisation. The integrated geometry validator can report on validity of building models, such as watertightness, manifoldness, or occurrences of self-intersections. In the case of invalid geometries, we can generate an approximation: geometry repair the with alpha wrapping algorithm, or reconstruction in lower LoD. We tested our implementation on two different real-world datasets — one in The Netherlands, and another one in the USA. The results showed that 95% (Dutch dataset) and 90% (US dataset) buildings were valid according to the ISO 19107 standard. Generated grids showed satisfactory quality as we observed monotonous convergence in simulations with grid convergence indices up to 3.8% for pressure and velocity variables. These results indicate that the workflow is suitable for typical urban microscale simulations.@en

This paper presents a new algorithm for filling holes in Level of Detail 2 (LoD2) building mesh models, addressing the challenges posed by geometric inaccuracies and topological errors. Unlike traditional methods that often alter the original geometric structure or impose stringent input requirements, our approach preserves the integrity of the original model while effectively managing a range of topological errors. The algorithm operates in three distinct phases: (1) pre-processing, which addresses topological errors and identifies pseudo-holes; (2) detecting and extracting complete border rings of holes; and (3) remeshing, aimed at reconstructing the complete geometric surface. Our method demonstrates superior performance compared to related work in filling holes in building mesh models, achieving both uniform local geometry around the holes and structural completeness. Comparative experiments with established methods demonstrate our algorithm’s effectiveness in delivering more complete and geometrically consistent hole-filling results, albeit with a slight trade-off in efficiency. The paper also identifies challenges in handling certain complex scenarios and outlines future directions for research, including the pursuit of a comprehensive repair goal for LoD2 models to achieve watertight 2-manifold models with correctly oriented normals. Our source code is available at https://github.com/tudelft3d/Automatic-Repair-of-LoD2-Building-Models.git@en

Objective Recent advancements in laser scanners and photogrammetry technology have significantly reduced the cost of acquiring 3D point clouds. Consequently, various types of point clouds have gradually become popular data sources for urban applications. The accurate registration of cross-source and multi^-temporal point clouds must be ensured before developing applications based on 3D point clouds. However, this is a challenging task owing to (1) the large amount of data to be considered, (2) the wide discrepancy in characteristics between cross-source point clouds, and (3) the significant changes in a scene represented by multi^-temporal point clouds. These data characteristics can harm the extraction and matching of registration primitives, resulting in the poor performance of marker^-free registration techniques. In this paper, we propose an automated, efficient, and marker^-free method for registering cross-source and multi^-temporal point clouds in urban areas. Methods The proposed registration method comprises three stages: keypoint generation, correspondence matching, and transformation estimation. (1) Keypoint generation. We generate object^-level virtual keypoints as registration primitives rather than directly extracting local features from point clouds, which are redundant and sensitive to outliers and missing data. Specifically, the ground points are first filtered out via the cloth simulation filtering algorithm. The remaining points are decomposed into planar segments by fitting planes in a region-growing manner. Finally, virtual keypoints are determined as the endpoints of intersecting line segments of two adjacent planes. (2) Correspondence matching. First, local triangles are constructed using the generated virtual keypoints as vertices to encode the relative spatial relationships among keypoints within a point cloud. Second, the triangle sets of both point clouds are mapped to a feature space where the triangles become 3D feature points. For each feature point in the source point cloud, we determine its closest point in the target point cloud, forming triangle pairs between the two point clouds. Finally, we propose an improved global matching approach with linear time complexity to extract correspondences encoded in the triangle pairs. (3) Transformation estimation. As cross-source and multi^-temporal point clouds are typically well^-leveled, registration can be achieved by aligning the two point clouds horizontally and translating them vertically. We use the horizontal coordinates of the correspondences to estimate the 2D horizontal transformation and their vertical coordinates to calculate the vertical translation. Results and Discussions We evaluated the effectiveness of the proposed method using large^-scale real^-world urban point clouds. The experimental data consist of six cross-source and multi^-temporal point clouds, including three airborne light detection and ranging (LiDAR) point clouds and three photogrammetric point clouds, which cover an urban area of 1. 8 km² in Rotterdam, the Netherlands. Each point cloud comprises a large number of points (approximately 20‒60 million points per point cloud; refer to Table 1 for details). Additionally, as the point clouds were collected over a long period of time, many of the objects in the scene have changed considerably. These two characteristics make them suitable for performing comprehensive evaluations of automatic marker^-free registration methods. To evaluate the registration results qualitatively, we visualized a randomly selected region (Fig. 7) and three manually selected buildings with varying architectural styles (Fig. 8). Despite the different characteristics of cross-source point clouds and the significant changes in scenes, the proposed method could accurately align all five registration pairs formed by the six experimental point clouds. To evaluate the registration results quantitatively, we calculated both matrix^-based errors (i. e., rotation and translation errors) as well as pointwise errors. The evaluation is summarized in Table 4. Our automatic registration results have an average pointwise error of 6.4 cm, whereas the average matrix^-based errors are 0.2′for rotation and 7.4 cm for translation. Furthermore, despite the massive size of the experimental point clouds, the proposed approach required only 105.7 s to achieve pairwise registration on average. Both qualitative and quantitative results demonstrate the effectiveness of the proposed method for registering cross-source and multi^-temporal urban point clouds. Conclusions A fully automated marker^-free registration approach is presented for cross-source and multi^-temporal point clouds in urban environments. Object^-level virtual keypoints are generated from urban point clouds as registration primitives, thereby overcoming the challenge of identifying valid corresponding features. By encoding rigid body spatial relations among the generated virtual keypoints, we establish correspondences between the source and target point clouds, resulting in efficient matching for large-scale urban scenes. Experiments on real^-world data demonstrate that the proposed method can automatically, accurately, and efficiently register cross-source and multi^-temporal point clouds in urban areas, indicating its practical utility. In the future, we would like to collect more data to test the robustness of the proposed method. Moreover, we intend to study the potential of the proposed matching algorithm in the fusion of general multi^-source data, e. g. , aligning 3D building point clouds with 2D building footprints.

@en

This document provides a description of the project “Computing volumes and surface areas including party walls for the 3DBAG dataset” which has been carried out between the 3D Geoinformation group at TU Del6, 3DGI, and RVO in the timeframe between November 2022 and October 2023. The goal of this project is to derive parameters from the 3DBAG that are relevant for energy consumption estimation, i.e. the enclosed volume of each building, as well as the party wall areas, the exterior wall areas, the ground floor areas and the roof areas. As the detection of the party wall (i.e. the portion of the building shell that is shared between two buildings (BAG-panden)) is the most complex task to solve, specifically for a large data set, the main goal of the project is to define, evaluate and implement a methodology to compute the area extents of party walls between adjacent buildings from the 3DBAG data set. The 3DBAG dataset was first released in March 2021. A first revised version was released in September 2021 which we used for our analysis carried out during the first part of this project. The latest (5th) version has been released in October 2023 based on which we generated the final data for this project. In this last version AHN4 has been incorporated. 3DBAG is a country-wide dataset containing all buildings in the Netherlands, modelled in multiple LoDs, and based on the international standard CityGML. According to CityGML, a building can be modelled as a single-part unique object, or as an aggregation of building parts, each one having its own geometry. Additionally, each building is a geographical feature that can have several aTributes (e.g. year of construction, number of storeys, etc.) and different geometries representing each one a specific Level of Detail (LoD). A graphical overview of the different LoDs according to CityGML v. 2.0 is given in Figure 1. In particular, the LoD2 allows differentiating between different thematic surfaces composing the building envelope. The geometries are semantically enriched and classified into GroundSurfaces, WallSurfaces and RoofSurfaces. In the case of LoD2, RoofSurfaces represent the main planar surface(s) of the roofs. Smaller roof structures like chimneys and dormers are generally absent if their size is too small with regard to the surveyed data used for the 3D reconstruction process (e.g. the Lidar point cloud density). The GroundSurfaces generally correspond to the planar extents of the roof surfaces projected onto the horizontal ground but they can also correspond to footprints. WallSurfaces connect vertically the Roof- and GroundSurfaces. This means that overhanging geometries (e.g. of roofs) lead to larger GroundSurfaces as in reality. But roof overhangs can also be represented. A graphical example can be seen comparing LoD2 and LoD3 in Figure 1. Finally, in LoD2 buildings there are no openings, i.e. neither doors nor windows. More details about CityGML v. 2.0 and the modelling rules for the buildings can be found in the technical specifications of the standard published by the Open Geospatial Consortium.@en

De 3D BAG bevat automatisch gereconstrueerde LoD2-modellen van alle panden in Nederland, en is voor het eerst gereconstrueerd in het voorjaar van 2021 op basis van AHN3.1 Op basis van AHN4 is een nieuwe versie van de 3D BAG gereconstrueerd, in een samenwerking tussen 3DGI en de onderzoeksgroep 3D Geoinformation (TU Delft). AHN4 is niet alleen van hogere actualiteit, maar heeft ook andere kenmerken dan AHN3. Voor de geactualiseerde versie van 3D BAG hebben we daarom onderzocht hoe beide datasets optimaal gebruikt kunnen worden.@en

Voor de berekening van omgevingsgeluid geproduceerd door weg- en railverkeer en industrie maakt een geluidexpert gebruik van een 3D-model van de omgeving. Dit 3D model bevat onder andere informatie over a) de terreinhoogte, b) gebouwen en c) geluidreflecterende/absorberende eigenschappen van de bodem. Sinds vorig jaar kunnen geluidsexperts gebruik maken van een automatisch gegenereerd en landsdekkend 3D Omgevingsmodel Geluid. Deze dataset is ontwikkeld in een samenwerking van RIVM, Kadaster en de 3D Geoinformation onderzoeksgroep van de TU Delft in opdracht van het ministerie van Infrastructuur en Waterstaat. [...]@en

In this paper, we present our workflow to automatically reconstruct three-dimensional (3D) building models based on two-dimensional building polygons and a lidar point cloud. The workflow generates models at different levels of detail (LoDs) to support data require-ments of different applications from one consistent source. Specific attention has been paid to make the workflow robust to quickly run a new iteration in case of improvements in an algorithm or in case new input data become available. The quality of the reconstructed data highly depends on the quality of the input data and is monitored in several steps of the process. A 3D viewer has been developed to view and download the openly available 3D data at different LoDs in different formats. The workflow has been applied to all 10 million buildings of the Netherlands. The 3D ser-vice will be updated after new input data becomes available.

@en

Satellite-Derived Bathymetry (SDB) can be calculated using analytical or empirical approaches. Analytical approaches require several water properties and assumptions, which might not be known. Empirical approaches rely on the linear relationship between reflectances and in-situ depths, but the relationship may not be entirely linear due to bottom type variation, water column effect, and noise. Machine learning approaches have been used to address nonlinearity, but those treat pixels independently, while adjacent pixels are spatially correlated in depth. Convolutional Neural Networks (CNN) can detect this characteristic of the local connectivity. Therefore, this paper conducts a study of SDB using CNN and compares the accuracies between different areas and different amounts of training data, i.e., single and multi-temporal images. Furthermore, this paper discusses the accuracies of SDB when a pre-trained CNN model from one or a combination of multiple locations is applied to a new location. The results show that the accuracy of SDB using the CNN method outperforms existing works with other methods. Multi-temporal images enhance the variety in the training data and improve the CNN accuracy. SDB computation using the pre-trained model shows several limitations at particular depths or when water conditions differ.

@en

We present a fully automatic approach for reconstructing compact 3D building models from large-scale airborne point clouds. A major challenge of urban reconstruction from airborne LiDAR point clouds lies in that the vertical walls are typically missing. Based on the observation that urban buildings typically consist of planar roofs connected with vertical walls to the ground, we propose an approach to infer the vertical walls directly from the data. With the planar segments of both roofs and walls, we hypothesize the faces of the building surface, and the final model is obtained by using an extended hypothesis-and-selection-based polygonal surface reconstruction framework. Specifically, we introduce a new energy term to encourage roof preferences and two additional hard constraints into the optimization step to ensure correct topology and enhance detail recovery. Experiments on various large-scale airborne LiDAR point clouds have demonstrated that the method is superior to the state-of-the-art methods in terms of reconstruction accuracy and robustness. In addition, we have generated a new dataset with our method consisting of the point clouds and 3D models of 20k real-world buildings. We believe this dataset can stimulate research in urban reconstruction from airborne LiDAR point clouds and the use of 3D city models in urban applications@en

Satellite-Derived Bathymetry (SDB) has been used in many applications related to coastal management. SDB can efficiently fill data gaps obtained from traditional measurements with echo sounding. However, it still requires numerous training data, which is not available in many areas. Furthermore, the accuracy problem still arises considering the linear model could not address the non-relationship between reflectance and depth due to bottom variations and noise. Convolutional Neural Networks (CNN) offers the ability to capture the connection between neighbouring pixels and the non-linear relationship. These CNN characteristics make it compelling to be used for shallow water depth extraction. We investigate the accuracy of different architectures using different window sizes and band combinations. We use Sentinel-2 Level 2A images to provide reflectance values, and Lidar and Multi Beam Echo Sounder (MBES) datasets are used as depth references to train and test the model. A set of Sentinel-2 and in-situ depth subimage pairs are extracted to perform CNN training. The model is compared to the linear transform and applied to two other study areas. Resulting accuracy ranges from 1.3m to 1.94m, and the coefficient of determination reaches 0.94. The SDB model generated using a window size of 9x9 indicates compatibility with the reference depths, especially at areas deeper than 15m. The addition of both short wave infrared bands to the four visible bands in training improves the overall accuracy of SDB. The implementation of the pre-trained model to other study areas provides similar results depending on the water conditions.

@en

3D-toepassingen gaan vaak gepaard met de wens om gebouwen met dakvormen te modelleren. Na jaren onderzoek en ontwikkeling hebben we in Delft een methode gerealiseerd die volledig automatisch dakvormen (LoD2) reconstrueert uit puntenwolken en 2D-pandpolygonen. Met deze methode hebben we 3D-modellen gegenereerd voor alle 10 miljoen BAG-panden in Nederland, de eerste open 3D-dataset op dit detailniveau. Niet alle toepassingen zijn gebaat bij dit detailniveau. Daarom reconstrueren we in hetzelfde proces ook andere detailniveaus. Het volledig automatisch proces zorgt ook in de toekomst voor consistentie als nieuwe modellen worden geconstrueerd met actuele input-data. Bovendien monitoren we verschillende kwaliteitsparameters die gebruikers kunnen helpen bij de juiste toepassing van de data. @en

3D city models are playing a growing role worldwide as sources of integrated information upon which different urban applications are developed. In the context of urban planning and design, semantic 3D city models can provide plenty of qualitative and quantitative information about the urban context and of the area(s) to be transformed. This paper takes inspiration and continues a work recently published in which several design parameters and Key Performance Indicators are computed from a semantic 3D city model, and later used in a GIS-supported urban design process to develop a new area. As many of such parameters are derived from the gross volume of the building stock, this paper investigates whether and to which extent different building stock models might affect the estimation of the gross volume. The study is carried out in anticipation of the upcoming LoD2-based, country-wide model of the Netherlands that is being finalised by our team. At the same time, the paper investigates whether and which information can be obtained regarding the quality of the LoD2 model from a comparison with the LoD1 one, with a focus on volume calculation.

@en

Fully automated reconstruction of high-detail building models on a national scale is challenging. It raises a set of problems that are seldom found when processing smaller areas, single cities. Often there is no reference, ground truth available to evaluate the quality of the reconstructed models. Therefore, only relative quality metrics are computed, comparing the models to the source data sets. In the paper we present a set of relative quality metrics that we use for assessing the quality of 3D building models, that were reconstructed in a fully automated process, in Levels of Detail 1.2, 1.3, 2.2 for the whole of the Netherlands. The source data sets for the reconstruction are the Dutch Building and Address Register (BAG) and the National Height Model (AHN). The quality assessment is done by comparing the building models to these two data sources. The work presented in this paper lays the foundation for future research on the quality control and management of automated building reconstruction. Additionally, it serves as an important step in our ongoing effort for a fully automated building reconstruction method of high-detail, high-quality models.

@en

Overheden moeten kunnen beoordelen of de geluidsbelasting op bijvoorbeeld een woonwijk binnen wettelijke limieten valt. Daarvoor moeten geluidsniveaus worden gesimuleerd. Het Kadaster, RIVM, RWS, IPO en TU Delft (3D Geoinformation) zijn in 2017 begonnen met een project om vanuit bestaande gegevens 3D-inputdata voor geluidsstudies te genereren, aansluitend op onze andere 3D-projecten (zoals bijvoorbeeld beschreven in de vorige Geo-Info). De algoritmes waren vorig jaar goed genoeg voor een landsdekkende uitrol. Sinds februari 2021 is dit 3D-omgevingsmodel voor Geluid als open data via PDOK beschikbaar.@en

Three-dimensional city models are essential to assess the impact that environmental factors will have on citizens, because they are the input to several simulation and prediction software. Examples of such environmental factors are noise (Stoter et al., 2008), wind (Garcı́a-Sánchez et al., 2014), air pollution (Ujang et al., 2013), and temperature (Hsieh et al., 2011; Lee et
al., 2013). However, those 3D models, which typically contain buildings and other man-made objects such as roads, overpasses, bridges, and trees, are in practice complex to obtain, and it is very time-consuming and tedious to reconstruct them manually. The software 3dfier addresses this issue by automating the 3D reconstruction process. It takes 2D geographical datasets (e.g., topographic datasets) that consist of polygons and “3dfies” them (as in “making them three-dimensional”). The elevation is obtained from an aerial point cloud dataset, and the semantics of the polygons is used to perform the lifting to the third dimension, so that it is realistic. The resulting 3D dataset is semantically decomposed/labelled based on the input polygons, and together they form one(many) surface(s) that aim(s) to be error-free: no self-intersections, no gaps, etc. Several output formats are supported (including
the international standards), and the 3D city models are optimised for use in different software.@en

As in many countries, in The Netherlands governmental organisations are acquiring 3D city models to support their public tasks. However, this is still being done within individual organisation, resulting in differences in 3D city models within one country and sometimes covering the same area: i.e. differences in data structure, height references used, update cycle, data quality, use of the 3D data etc. In addition, often only large governmental organisations can afford investing in 3D city models (and the required knowledge) and not small organisations, like small municipalities. To address this problem, the Dutch Kadaster is collaborating with the 3D Geoinformation research group at TU Delft to generate and disseminate a 3D city model covering the whole of the Netherlands and to do this in a sustainable manner, i.e. with an implementation that ensures periodical updates and that aligns with the 3D city models of other governmental organisations, such as large cities. This article describes the workflow that has been developed and implemented.

@en

Automatic building extraction and delineation from airborne LiDAR point cloud data of urban environments is still a challenging task due to the variety and complexity at which buildings appear. The Medial Axis Transform (MAT) is able to describe the geometric shape and topology of an object, but has never been applied for building roof outline extraction. It represents the shape of an object by its centerline, or skeleton structure instead of its boundary. Notably, end points of the MAT in principle coincide with corner points of building outlines. However, the MAT is sensitive to small boundary irregularities, which makes shape detection in airborne point clouds challenging. We propose a robust MAT-based method for detecting building corner points, which are then connected to form a building boundary polygon. First, we approximate the 2D MAT of a set of building edge points acquired by the alpha-shape algorithm to derive a so-called building roof skeleton. We then propose a hierarchical corner-aware segmentation to cluster skeleton points based on their properties which are the so-called separation angle, radius of the maximally inscribe circle, and defining edge point indices. From each segment, a corner point is then estimated by extrapolating the position of the zero radius inscribed circle based on the skeleton point positions within the segment. Our experiment uses point cloud datasets of Makassar, Indonesia and EYE-Amsterdam, The Netherlands. The average positional accuracy of the building outline results for Makassar and EYE-Amsterdam is 65 cm and 70 cm, respectively, which meet one-meter base map accuracy criteria. The results imply that skeletonization is a promising tool to extract relevant geometric information on e.g. building outlines even from far from perfect geographical point cloud data.

@en

Noise is one of the main problems in urban areas. To monitor and manage noise problems, governmental organisations at all levels are obliged to regularly carry out noise studies. The simulation of noise is an important part of these studies. Currently, different organisations collect their own 3D input data as required in noise simulation in a semi-automated way, even if areas overlap. This is not efficient, but also differences in input data may lead to differences in the results of noise simulation which has a negative impact on the reliability of noise studies. To address this problem, this paper presents a methodology to automatically generate 3D input data as required in noise simulations (i.e. buildings, terrain, land coverage, bridges and noise barriers) from current 2D topographic data and point clouds. The generated data can directly be used in existing noise simulation software. A test with the generated data shows that the results of noise simulation obtained from our generated data are comparable to results obtained in a current noise study from practice. Automatically generated input data for noise simulation, as achieved in this paper, can be considered as a major step in noise studies. It does not only significantly improve the efficiency of noise studies, thus reducing their costs, but also assures consistency between different studies and therefore it improves the reliability and reproducibility. In addition, the availability of countrywide, standardised input data can help to advance noise simulation methods since the calculation method can be adopted to improved ways of 3D data acquisition and reconstruction.@en