3D Urban Models Research Articles

Comparing the accuracy of 3D urban olive tree models detected by smartphone using LiDAR sensor, photogrammetry and NeRF: a case study of ’Ascolana Tenera’ in Italy

Abstract. Rapid urban growth makes green space management crucial to improve citizens’ well-being. Urban olive trees characterize the Italian landscapes and their culture. This study explores different methodologies for urban tree assessment in this context, using an iPhone 14 Pro Max. These included: 1) its integrated Light Detection and Ranging (LiDAR) sensor using the Recon3D app, 2) its camera with Structure from Motion (SfM) techniques, and 3) its camera for generating 3D models using Neural Radiance Fields (NeRF). Additionally, a professional Mobile Laser Scanner (MLS), was used for comparison. Total height (H), canopy base height (CBH) and canopy volume (CV) measurements were extracted using both CloudCompare and allometric formulas. The main aim of this paper is to compare the 3D models of olive trees obtained from low-cost sensors with those generated from the MLS, which is a more accurate device but comes with significantly higher costs. The results, in terms of RMSE (iPhone LiDAR - H: 0.46 m, CBH: 0.12 m, CV: 15.66 m3; iPhone-SfM - H: 0.95 m, CBH: 0.19 m, CV: 25.85 m3; iPhone-NeRF - H: 1.26 m, CBH: 0.31 m, CV: 33.79 m3), bias and volume differences, reveal that the smartphone, in all the methodologies, tends to underestimate measurements as the size of the trees increases. This is due to the higher MLS range of acquisition. Despite these limitations, low-cost solutions like smartphone-based methods can be a viable alternative given their economic accessibility.

Research on data processing of 3D modeling by images based on helicopter oblique photogrammetry

Abstract The use of tilting photogrammetry technology to build a refined urban 3D model has become the industry research hotspot with the rapid development of China’s “digital city.” To investigate and analyze the methodology of 3D data modeling using helicopter oblique photogrammetry, a 3D model was generated for a study area covering approximately 34 km2. This paper delves into the technical process of 3D modeling data processing utilizing helicopter oblique photogrammetry, and it examines the precision of the model results alongside a comprehensive technical analysis. The results show that the results of the process are consistent with the relevant specifications of the first-order 3D model landscape. Compared with the traditional 3D model, the method has obvious progress in efficiency and has a very wide application prospect.

3D LoD2 modelling of Halong City based on UAV point cloud

3D urban building models are crucial for linking, converging, and integrating economic and social urban data. They are extensively utilized in numerous domains such as smart city development, comprehensive social management, and emergency decision-making. Advanced technologies like affordable UAV (Unmanned Aerial Systems) imagery enable a greater level of automation in data acquisition compared to traditional digital photogrammetry methods. The main objective of this research is to build a 3D LoD2 CityGML model with dense point clouds from UAV images. This study presents a completed workflow for generating 3D CityGML models of the city at LoD2 using UAV data. The use of dense point cloud data from UAV technology in the experimental area has been performed using a DJI Phantom 4 Pro. The original point clouds should be denoised using the statistical outlier remover (SOR), the main goal is to reduce noise while preserving the building's geometry. After that, the point clouds of object features were vectored for the level of detail 2 (LoD2) of the object's 3D volume corresponding to its actual height, and objects belonging to the Feature Class 3D layer will represent LoD2 on SketchUp Pro 2021 software to generate a highly accurate 3D model. The evaluation results show that the square errors calculated from the test points for the three axes X, Y, Z are 1.4 cm, 1.6 cm, 1.7 cm, respectively. Conducting research to choose the UAV photography method aims to offer an efficient and cost-effective solution, saving time and human resources, to address the 3D mapping challenges in urban areas across Vietnam.

Large-Scale Solar Potential Analysis in a 3D CAD Framework as a Use Case of Urban Digital Twins

Solar radiation impacts diverse aspects of city life, such as harvesting energy with PV panels, passive heating of buildings in winter, cooling the loads of air-conditioning systems in summer, and the urban microclimate. Urban digital twins and 3D city models can support solar studies in the process of urban planning and provide valuable insights for data-driven decision support. This study examines the calculation of solar incident radiation at the city scale in Sofia using remote sensing data for the large shading context in a mountainous region and 3D building data. It aims to explore the methods of geometry optimisation, limitations, and performance issues of a 3D computer-aided design (CAD) tool dedicated to small-scale solar analysis and employed at the city scale. Two cases were considered at the city and district scales, respectively. The total face count of meshes for the simulations constituted approximately 2,000,000 faces. A total of 64,379 roofs for the whole city and 4796 buildings for one district were selected. All calculations were performed in one batch and visualised in a 3D web platform. The use of a 3D CAD environment establishes a seamless process of updating 3D models and simulations, while preprocessing in Geographic Information System (GIS) ensures working with large-scale datasets. The proposed method showed a moderate computation time for both cases and could be extended to include reflected radiation and dense photogrammetric meshes in the future.

Optimizing Urban Layout: A System Dynamics, Artificial Intelligence, and 3D Urban Information Model Approach for Active Management of City Complexity

Optimizing Urban Layout: A System Dynamics, Artificial Intelligence, and 3D Urban Information Model Approach for Active Management of City Complexity

Integrating geospatial data and street‐view imagery to reconstruct large‐scale 3D urban building models

Abstract3D urban building modeling is a vital foundational step for building Digital Twins and Smart Cities. In response to existing challenges, such as high time costs, complex production processes, and low consistency with real‐world textures in large‐scale 3D urban building modeling methods, this research proposes a reconstructing 3D urban building models (3DUBM) approach that integrates geospatial data and street view. The approach achieves an enhanced generation of large‐scale 3DUBMs. Based on open geospatial data and street‐view imagery (SVI), the approach was tested in modeling experiments conducted in Shanghai, Hongkong, and Nanjing. Furthermore, a dataset covering unique blocks of 30 cities in China was constructed to demonstrate the approach's characteristics of large coverage, high time efficiency, high model quality and low economic cost. The accuracy of texture mapping from SVI to 3DUBM reached 85%. This achievement has significant economic value in bridging the gap in the production of large‐scale and low‐cost 3DUBM data, promoting the construction of Digital Twins, Smart Cities, and Real‐world 3D modeling.

Urban 3D Modeling as a Precursor of City Information Modeling and Digital Twin for Smart City Era: A Case Study of the Narmak Neighborhood of Tehran City, Iran

Urban 3D Modeling as a Precursor of City Information Modeling and Digital Twin for Smart City Era: A Case Study of the Narmak Neighborhood of Tehran City, Iran

Extending CityGML with public input – social ADE

PurposeThis paper aims to enrich the 3D urban models with data contributed by citizens to support data-driven decision-making in urban infrastructure projects. We introduced a new application domain extension to CityGML (social – input ADE) to enable citizens to store, classify and exchange comments generated by citizens regarding infrastructure elements. The main goal of social – input ADE is to add citizens’ feedback as semantic objects to the CityGML model.Design/methodology/approachFirstly, we identified the key functionalities of the suggested ADE and how to integrate them with existing 3D urban models. Next, we developed a high-level conceptual design outlining the main components and interactions within the social-input ADE. Then we proposed a package diagram for the social – input ADE to illustrate the organization of model elements and their dependencies. We also provide a detailed discussion of the functionality of different modules in the social-input ADE.FindingsAs a result of this research, it has seen that informative streams of information are generated via mining the stored data. The proposed ADE links the information of the built environment to the knowledge of end-users and enables an endless number of socially driven innovative solutions.Originality/valueThis work aims to provide a digital platform for aggregating, organizing and filtering the distributed end-users’ inputs and integrating them within the city’s digital twins to enhance city models. To create a data standard for integrating attributes of city physical elements and end-users’ social information and inputs in the same digital ecosystem, the open data model CityGML has been used.

A Concept for 3D Geological and Urban Subsurface Modeling with a Unified Voxel Model Examined by a Case Study for the City Center of Stuttgart (Baden-Württemberg), Germany

A Concept for 3D Geological and Urban Subsurface Modeling with a Unified Voxel Model Examined by a Case Study for the City Center of Stuttgart (Baden-Württemberg), Germany

Deep Learning based Semantic Segmentation for Buildings Detection from Remote Sensing Images

Building extraction from remote sensing images is the process of automatically identifying and extracting the boundaries of buildings from high-resolution aerial or satellite images. The extracted building footprints can be used for a variety of applications, such as urban planning, disaster management, city development, land management, environmental monitoring, and 3D modeling. The results of building extraction from remote sensing images depend on several factors, such as the quality and resolution of the image and the choice of algorithm.The process of building extraction from remote sensing images typically involves a series of steps, including image pre-processing, feature extraction, and classification. Building extraction from remote sensing images can be challenging due to factors such as varying building sizes and shapes, shadows, and occlusions. However, recent advances in deep learning and computer vision techniques have led to significant improvements in the accuracy and efficiency of building extraction methods. This research presents a deep learning semantic segmentation architecture-based model for developing building detection from high resolution remote sensing images. The open-source Massachusetts dataset is used to train the suggested UNet architecture. The model is optimized using the RMSProp algorithm with a learning rate of 0.0001 for 100 epochs. After 1.52 hours of training on Google Colab the model achieved an 83.55% F1 score, which indicates strong precision and recall.

Multi-source point cloud registration for urban areas using a coarse-to-fine approach

ABSTRACT The foundational step in constructing a digital twin involves transforming the physical world into an immersive 3D virtual environment. Unmanned aerial vehicle (UAV)-based photogrammetry, mobile mapping system (MMS), and terrestrial laser scanning (TLS) serve as powerful tools for 3D reconstruction of urban environments. Given the distinctive strengths and weaknesses of each sensor, a multi-source point cloud registration technique is imperative to achieve a detailed and precisely geolocated 3D urban model. Hence, we developed coarse-to-fine approach methods, called building exterior wall-based (BEWB) and building outline-based (BOB) algorithms, to register point clouds captured by diverse sensors in urban scenes. The BEWB algorithm coarsely registers urban point clouds by extracting building exterior walls, establishing correspondence points, and effectively removing outliers within this correspondence point set. The BOB algorithm precisely registers the urban point clouds acquired from multiple sensors by leveraging building outlines and points corresponding to the ground of the point clouds. To validate the proposed algorithms, we initially registered a UAV-based photogrammetry point cloud with the MMS point cloud and subsequently registered the TLS point clouds. Comprehensive quantitative and qualitative analyzes of the results demonstrate that our algorithms outperform existing methods in achieving precise registration. By successfully registering three distinct point clouds, we generated a comprehensive urban scene point cloud characterized by enhanced precision, point density, and geolocation accuracy.

A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net

In the automated modeling generated by oblique photography, various terrains cannot be physically distinguished individually within the triangulated irregular network (TIN). To utilize the data representing individual features, such as a single building, a process of building monomer construction is required to identify and extract these distinct parts. This approach aids subsequent analyses by focusing on specific entities, mitigating interference from complex scenes. A deep convolutional neural network is constructed, combining U-Net and ResNeXt architectures. The network takes as input both digital orthophoto map (DOM) and oblique photography data, effectively extracting the polygonal footprints of buildings. Extraction accuracy among different algorithms is compared, with results indicating that the ResNeXt-based network achieves the highest intersection over union (IOU) for building segmentation, reaching 0.8255. The proposed “dynamic virtual monomer” technique binds the extracted vector footprints dynamically to the original oblique photography surface through rendering. This enables the selective representation and querying of individual buildings. Empirical evidence demonstrates the effectiveness of this technique in interactive queries and spatial analysis. The high level of automation and excellent accuracy of this method can further advance the application of oblique photography data in 3D urban modeling and geographic information system (GIS) analysis.

Online Street View-Based Approach for Sky View Factor Estimation: A Case Study of Nanjing, China

The Sky View Factor (SVF) stands as a critical metric for quantitatively assessing urban spatial morphology and its estimation method based on Street View Imagery (SVI) has gained significant attention in recent years. However, most existing Street View-based methods prove inefficient and constrained in SVI dataset collection. These approaches often fall short in capturing detailed visual areas of the sky, and do not meet the requirements for handling large areas. Therefore, an online method for the rapid estimation of a large area SVF using SVI is presented in this study. The approach has been integrated into a WebGIS tool called BMapSVF, which refines the extent of the visible sky and allows for instant estimation of the SVF at observation points. In this paper, an empirical case study is carried out in the street canyons of the Qinhuai District of Nanjing to illustrate the effectiveness of the method. To validate the accuracy of the refined SVF extraction method, we employ both the SVI method based on BMapSVF and the simulation method founded on 3D urban building models. The results demonstrate an acceptable level of refinement accuracy in the test area.

Towards digital twinning for multi-domain simulation workflows in urban design: a case study in Gothenburg

This work proposes an automated workflow using digital twinning for multi-domain environmental performance analysis of urban developments. Digital twins can potentially provide a common basis for multi-domain simulations and help overcome data availability and interoperability issues. The proposed workflow consists of five steps: (1) creating a procedural urban 3D model, (2) generating design alternatives parametrically, (3) exporting the context and each design alternative to each simulation tool, (4) running simulations for wind comfort, energy demand, and noise for each design alternative, and (5) combining and visualizing the simulation results using the digital twin. The workflow was applied to a neighbourhood in Sweden, the resultsreveal significant reduction in manual work when applying multiple simulation software for different domains. This is one step forward in streamlining the workflow for urban analysis, crucial for multi-domain optimization. In the future, further domains and simulation tools can be added to the workflow.

Research on Urban Building Parametric Modelling Method Based on CityEngine

With the advancement of technology and the development of cities, urban planning and management methods are also constantly improving. From paper-based assignments to modern digitization, new technologies have enabled more efficient design and management for cities. 3D modeling can used to simulate the urban environment, which can assist in urban planning and management. However, large-scale modeling cannot be achieved through existing modeling methods, and there are still some shortcomings in the maintenance of the model. Therefore, this article proposes a Computer Generated Architecture (CGA) parametric 3D modeling method based on CityEngine. Research on expanding and customizing modeling rules to create indoor and outdoor modeling rule templates for buildings and methods for generating urban 3D models have been carried out. The results have shown that the completed model can be displayed on different platforms thanks to parameterized modeling. The model can be modified easily and directly applied to the analysis and decision-making of urban planning schemes.

Construction of a sensor-based urban three-dimensional landscape network visualization model

In the process of urbanization, the design and planning of urban landscapes have become increasingly important. Aiming at the shortcomings of traditional urban planning models such as poor visual presentation and low error rate in landscape creation, this article utilized remote sensing technology to collect vegetation and building landscape data and used geographic information systems (GIS) to process and analyze the collected landscape data. With the help of analyzed data, a visualization model of urban three-dimensional (3D) landscape network was constructed using sensors and modeling techniques. Sensors were used to achieve visualization display and management of urban landscape network, enabling better development of urban 3D landscape visualization models. The user satisfaction rate of the sensor based 3D landscape visualization model was over 92.4% and the average error rate of landscape creation after 20 experiments was 3.9835%. Building a 3D urban landscape visualization model based on sensors could effectively improve user satisfaction with the model’s visualization, provide better visualization services to users and help designers better create landscapes, improving the accuracy of landscape creation.

Full-automatic high-precision scene 3D reconstruction method with water-area intelligent complementation and mesh optimization for UAV images

ABSTRACT Fast and high-precision urban scene 3D modeling is the foundational data infrastructure for the digital earth and smart cities. However, due to challenges such as water-area matching difficulties and issues like data redundancy and insufficient observations, existing full-automatic 3D modeling methods often result in water-area missing and many small holes in the models and insufficient local-model accuracy. To overcome these challenges, full-automatic high-precision scene 3D reconstruction method with water-area intelligent complementation on depth maps and mesh optimization is proposed. Firstly, SfM was used to calculated image poses and PatchMatch was used to generated initial depth maps. Secondly, a simplified GAN extracted water-area masks and ray tracing was used achieve high-precision auto-completed water-area depth values. Thirdly, fully connected CRF optimized water-areas and arounds in depth maps. Fourthly, high-precision 3D point clouds were obtained using depth map fusion based on clustering culling and depth least squares. Then, mesh was generated and optimized using similarity measurement and vertex gradients to obtain refined mesh. Finally, high-precision scene 3D models without water-area missing or holes were generated. The results showed that: to compare with the-state-of-art ContextCapture, the proposed method enhances model completeness by 14.3%, raises average accuracy by 14.5% and improves processing efficiency by 63.6%.

Sat2Map: Reconstructing 3D Building Roof from 2D Satellite Images

Three-dimensional (3D) urban models have gained interest because of their applications in many use cases, such as disaster management, energy management, and solar potential analysis. However, generating these 3D representations of buildings require lidar data, which is usually expensive to collect. Consequently, the lidar data are not frequently updated and are not widely available for many regions in the US. As such, 3D models based on these lidar data are either outdated or limited to those locations where the data is available. In contrast, satellite images are freely available and frequently updated. We propose sat2Map , a novel deep learning-based approach that predicts building roof geometries and heights directly from a single 2D satellite image. Our method first uses sat2pc to predict the point cloud by integrating two distinct loss functions, Chamfer Distance and Earth Mover’s Distance, resulting in a 3D point cloud output that balances overall structure and finer details. Additionally, we introduce sat2height , a height estimation model that estimates the height of the predicted point cloud to generate the final 3D building structure for a given location. We extensively evaluate our model on a building roof dataset and conduct ablation studies to analyze its performance. Our results demonstrate that sat2Map consistently outperforms existing baseline methods by at least 18.6%. Furthermore, we show that our refinement module significantly improves the overall performance, yielding more accurate and fine-grained 3D outputs. Our sat2height model demonstrates a high accuracy in predicting height parameters with a low error rate. Furthermore, our evaluation results show that we can estimate building heights with a median mean absolute error of less than 30 cm while still preserving the overall structure of the building.

A 3D urban scene reconstruction enhancement approach based on adaptive viewpoint selection of panoramic videos

AbstractThe widely used unmanned aerial vehicle oblique photogrammetry often suffers from information loss in complex urban environments, leading to geometric and textural defects in the resulting models. In this study, a close‐range panoramic optimal viewpoint selection assisted 3D urban scene reconstruction enhancement method is proposed for areas prone to defects. We first introduce the ground panoramic data acquisition equipment and strategy, which are different from those of the single‐lens supplementary photography method. Data acquisition is accomplished through a single and continuous surround‐style collection approach. The full coverage of the panoramic video in the space–time dimension enables the acquisition of texture details without considering camera station planning. Then, a panoramic multiview image generation approach is proposed. Adaptive viewpoint selection is achieved using unbiased sampling points from the rough scene model, and viewpoint optimisation is adopted to ensure sufficient image overlap and intersection effects, thus improving the scene reconstructability. Finally, the 3D model is generated by photogrammetric processing of the panoramic multiview images, resulting in an enhanced modelling effect. To validate the proposed method, we conducted experiments using real data from Qingdao, China. Both the qualitative and quantitative results demonstrate a significant improvement in the quality of geometric and textural reconstruction. The tie‐point reprojection errors are less than 1 pixel, and the registration accuracy with the model from oblique photogrammetry is comparable to that of optimised‐view photography. By eliminating the need for on‐site camera station planning or manual flight operations and effectively minimising the redundancy of panoramic videos, our approach significantly reduces the photography and computation costs associated with reconstruction enhancement. Thus, it presents a feasible technical solution for the generation of urban 3D fine models.

Research on 3D urban landscape digital modeling method based on image processing technology

Research on 3D urban landscape digital modeling method based on image processing technology