Conference Agenda

Digital Twins (DTs) for cities represent a new trend for city planning and management, enhancing three-dimensional modeling and simulation of cities. While progress has been made in this research field, the current scientific literature mainly focuses on the use of semantically segmented point clouds to develop 3D city models for DTs. However, this study discusses a new reflection that argues on directly integrating the results of semantic segmentation to create the skeleton of the DTs and uses enriched semantically segmented point clouds to perform targeted simulations without generating 3D models. The paper discusses to what extent enriched semantic 3D point clouds can replace semantic 3D city models in the DTs scope. Ultimately, this research aims to reduce the cost and complexity of 3D modeling to fit some DTs requirements and address its specific needs. New perspectives are set to tackle the challenges of using semantic 3D point clouds to implement DTs for cities.

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 will be released when the paper is accepted.

3D spatial data are widely used to simulate various urbanistic phenomena, thanks to their valuable semantic, geometric and topologic information. CityGML is a highly adopted data standard for semantic 3D city models, providing a standardized description of the cityscape that enables interoperability across different stakeholders. When future scenarios for urban development are simulated, the simulation results can be visualized and further analyzed in synthetically generated 3D city models. However, land use regulations are often overlooked when generating synthetic 3D city models for simulation purposes, despite some regulatory urban constraints having a direct impact on simulation results. For instance, the roof shape is highly correlated with building solar energy potential, while the zoning maximum allowed number of apartments directly influences the buildings' urban density estimation. Therefore, integrating such constructability knowledge within 3D city models is crucial. This paper proposes a framework for mapping urban planning rules defined in the German XPlanung standard onto 3D city models structured in compliance with CityGML to ensure legislative validity and real-life applicability. We review related work, discuss the structure of CityGML and the main elements concerned by urbanistic laws, explain the main concepts of XPlanung, and investigate the mapping of regulatory information with CityGML entities. In conclusion, this paper provides a conceptual framework for bridging the gap between urban planning regulations and 3D city models, highlighting the importance of integrating land use regulations into synthetic 3D city models to improve the accuracy of urban simulations. The proposed approach contributes to ensuring that the generated 3D City model satisfies the binding constructability rules by incorporating important urban planning regulations defined in XPlanung.

Visual, autonomous, object-based outdoor vehicle localization premise detailed object-based maps. Semantic-rich and qualitative Level of detail 3 (LOD3) building models fulfill these requirements, but only a few real-world city models are available. These models are mainly reconstructed by LiDAR, have a cost benefit, scalability and reconstruction complexity
problem. Challenging the issues, we propose an alternative data acquisition approach for LOD3 model reconstruction primarily based on images. Thus, we created a moveable handcart mounted height-adjustable, high-precision gimbal. The gimbal enables 360°poses of camera, LiDAR rangefinder, inertial measuring unit. Additionally, GNSS RTK is used for absolute positioning. Our system is capable to record data and ground truth data in one step. The paper is about the system design, data processing and validation of the proposed reconstruction approach. Resulting real-world reconstruction accuracies are in the millimeter to low centimeter range. So, our system is compared in discussion with competing systems.

Urban Digital Twins have received significant attention in recent years due to their economic and research importance. Although many definitions exist, the general consensus agrees on a continuous two way data flow between a physical entity and its virtual counterpart in a digital twin. In the context of smart cities and semantic 3D city models, however, no major breakthrough in realizing such complex change detection and analysis systems has yet been achieved. While several methods for change detection in semantic 3D city models have been proposed, the analysis of found changes, especially the identification of patterns among a large number of changes, has not been given as much attention. Without a proper handling of patterns, it is difficult to provide useful interpretation of changes with respect to stakeholders. Therefore, this research proposes a framework to define, detect and decipher complex semantic change patterns in semantic 3D city models. The approach provides a central rule network to describe aggregation relations between changes as well as methods to identify and capture detected change patterns directly in the graph representation of a city model.