- Project description
- Use case
- Project partners

Fraunhofer IGD’s technologies make it possible to identify appropriate landmarks in aerial photos that account for no-fly zones (such as over airports, federal waterways or wind turbines) in an automated process.
The research project “fAIRport” seeks to automatically define no-fly zones for drones. The project, funded with a total of €800,000 from the Federal Ministry of Transport and Digital Infrastructure as part of the “mFUND” (“Modernity Fund”) subsidization guideline, started on May 1, 2020 under the coordination of Fraunhofer IGD. Together with Deutsche Flugsicherung GmbH and the IT startup wetransform, IT experts in the fields of object detection, geodata visualization and artificial intelligence will be working for the next three years on a solution for integrating unmanned flying objects into regulated German airspace.
Commercial drone use only with clear regulation
Drones are more than just a novel techno gadget or backyard toy. The commercial potential, e.g., for inspecting buildings and bridges or surveying terrain, is enormous. A lack of airspace regulation for unmanned aircraft, however, prevents broad commercial use in Germany. Under § 21 German Air Traffic Regulations, the use of controlled airspace is only allowed with prior clearance. For commercial drone use, however, flights even beyond the pilot’s visual range are essential. This is why Deutsche Flugsicherung, which is given the official duty of controlling air traffic, wishes to make available a high-quality geospatial dataset for drone no-fly zones, allowing drone pilots to use Deutsche Flugsicherung’s traffic management system (UTM) to make sure the drone remains in approved areas even when out of sight.
No-fly zones defined with artificial intelligence
Implementation is based on aerial photos and geodata. Fraunhofer IGD’s technologies make it possible to identify appropriate landmarks in aerial photos that account for no-fly zones (such as over airports, federal waterways or wind turbines) in an automated process. Machine vision and learning methods are able to reliably detect structures and patterns and correctly classify them. Only with the help of artificial intelligence (AI) is it possible to rapidly identify drone no-fly zones for all of Germany and integrate them into the system. Manually this process would take far too long and Germany would miss the opportunity to join the commercial drone market.
The challenge: standardizing geoinformation
Information from aerial photos is supplemented by geoinformation from various sources. The heterogeneity of this information is a major challenge. The goal is to visually process all data for the user in an easily understandable way -- only this guarantees a transparent view and the data helps with immediate decision-making. To accomplish this, a platform is being developed with AI-based computer vision algorithms to automatically collect, process, virtually integrate and, ultimately, visually provide flight-relevant geoinformation. This is the job of the technology by wetransform GmbH -- a startup of researchers from Fraunhofer IGD who went into business for themselves in 2014 with their expertise in geodata harmonization.
Supported by:
As part of the mFUND research initiative, the BMVI has been funding research and development projects relating to data-based digital applications for mobility 4.0 since 2016. in addition to financial support, mFUND also supports networking between players from politics, business and research with various event formats and access to the mCLOUD data portal. Further information can be found at www.mfund.de.
Deutsche Flugsicherung GmbH, municipalities, authorities and organisations with safety responsibilities
Deutsche Flugsicherung GmbH
Wetransform GmbH