About this role
We want an earth that is worth living on. Our applied research in Circular Economy, Carbon Management, Green Hydrogen and Local Energy Systems makes concrete contributions to achieving the 17 Sustainable Development Goals of the United Nations. As an institute of the Fraunhofer-Gesellschaft, we show how to not only master challenges, but grow with them. We push boundaries, think ahead and shape the future with applied research. Diverse perspectives and approaches strengthen creativity and innovation in our scientific work.
Would you like to help us shape a sustainable world? We are looking for reinforcement!
Tire abrasion particles nowadays account for the majority of a vehicle’s harmful fine particulate matter emissions. The amount of abrasion generated depends not only on the vehicle and driving style but, above all, on the structure of the road surface. Fraunhofer UMSICHT has been modeling tire abrasion for years (TWM) – but one key component is missing: a reliable classification of road surfaces based on their abrasiveness. This would require large-scale surveys of roads, which is virtually impossible with conventional measurement techniques.
This is where your work comes in. Our hypothesis: Photographic data collection and AI-supported image analysis make it possible to classify road surfaces on a large scale. With support from the Fraunhofer Institute for Industrial and Technological Mathematics (ITWM), you will investigate whether typical abrasion classes can be derived from surface images – thereby laying the foundation for a method that can later be used on a mobile measurement platform (REDAR).
Be part of change
- You will set up a laboratory measurement system consisting of camera technology and lighting and optimize it for the reproducible capture of surface structures
- You will create a training dataset consisting of surface images with known abrasiveness or abrasiveness to be determined as part of this work
- You will develop an AI-based image analysis method and cluster the surfaces according to characteristic wear features (in collaboration with the Fraunhofer Institute for Industrial Mathematics ITWM)