KityVR - Artificial Intelligence for the Generation of CityGML Models and VR Visualization

The development of 3D city models enables the integration of city and building levels into a single model that contains both semantic and geometric information. These models can be used to help stakeholders such as policymakers, city planners, energy providers and suppliers, and citizens make decisions and improve communication and public relations. The highest form of visualization in this area is the use of virtual reality technology. CityGML is an international, widespread standard of the Open Geospatial Consortium for the modeling, storage and exchange of 3D city models; the Open Geospatial Consortiums regards the connection between virtual reality and CityGML as one of the greatest challenges in research and development. In this project two central research aspects in the area of ​​3D city models are addressed. (i) How can virtual reality be used as the highest form of visualization in the area of ​​3D city models? What use cases are there for virtual reality in the area of ​​3D city models? Answers to these questions are developed together with stakeholders and users; the focus is on energy-relevant applications. In the project, a methodology is being developed that enables automatic creation of virtual reality content from CityGML models in combination with energy-relevant extensions such as Energy ADE; Furthermore, the results of dynamic simulation results of energetic analyzes such as the electricity, heating and cooling requirements of a district are shown virtually. Finally, possibilities and limits of virtual reality in the field of 3D city modeling are explored in coordination with relevant stakeholders. (ii) The modeling of the energy structure of larger urban units is characterized by a lack of descriptive input data. In many cases, data sets are incomplete or certain use cases require additional information that is not represented in the corresponding data model; Furthermore, it can be assumed that virtual reality applications require additional data that is neither contained in the current CityGML format nor in ADE extensions. In all of these cases, an "enrichment" of the original data record is necessary in order to provide all the necessary data. Artificial intelligence and statistical methods are promising here: Missing information is calculated using other attributes and heuristic approaches. The planned project is embedded in international developments and projects in the CityGML and Energy ADE area as well as in the BIM2Sim and BIM2CityGML area.