Adaptive geometric-semantic multi-LOD road infrastructure construction model of the cyber-physical system (CPS) of the road (B01)

• Subject Area: Geodesy, Photogrammetry, Remote Sensing, Geoinformatics, Cartography
• Term: since 2022
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 453596084

In TP B01, an adaptive geometric-semantic building model (GSM) with several abstraction levels is developed, which enables the spatial multi-scale representation of the real existing object and, thus, serves as a homogeneous spatial reference for all geometry-related tasks in the SFB/TRR 339. The automatic model derivation is based on the combination of computational geometry, knowledge-based approaches and machine learning methods. The GSM data can be used in different levels of detail (LOD) for simulations, visualizations and other purposes. For the description of the geometric-semantic reliability of the data, a novel combined quality measure is developed that allows for an uncertainty quantification for the required LOD.

• DFG Programme: CRC/Transregios
• Subproject of: TRR 339: Digital twin of the road system – Physical-informational representation of the future road system
• Major Instrumentation: UAV-Laserscanner
• Instrumentation Group: 0550 Sichtweitemeßgeräte, Wolkenmesser
• Applicant Institution: Technische Universität Dresden
• Project Head: Professor Dr.-Ing. Jörg Blankenbach