Currently, there is no automated collection of condition data for German Autobahnen. An up-to-date database and automated assessment of the quality of individual stretches of highway would be important, for example, in order to initiate suitable maintenance measures at an early stage and thus prevent cost-intensive long-term damage. A modern highway network also holds great economic potential, for example in the field of autonomous driving.
The project goal is to create the basis for automatic and cost-efficient condition and inventory monitoring of the German Autobahn network using artificial intelligence (AI) and machine learning (ML) methods (feasibility study). This will lay the foundation for a digital twin of the Autobahn, on which a comparison (anomaly detection) of conditions can then take place using AI algorithms in the field of computer vision. In this way, relevant information for Autobahn operations, such as lane conditions or signage, can be automatically detected and extracted from the data.
Video data from test routes are annotated in close cooperation with Hessen Mobil and automatically evaluated using Deep Learning methods in the field of image processing. For this purpose, various machine learning models are trained and the algorithms are extended according to the specific problem. In this way, changes to static objects such as crash barriers are automatically detected. The long-term viability of the concept is being tested with the involvement of the Autobahn GmbH of the federal government.
- Project on BMVI website
- FKZ: VB18F1043A
- Project Volume: 124.996 €
- Project Duration: 12/2019 – 12/2020
- Associated Partner:
|Hessen Mobil Straßen und Verkehrsmanagement, Wiesbaden||Die Autobahn GmbH des Bundes, Berlin|