Master's Thesis: Typing of Road Surfaces Using AI-Supported Image Analysis

Fraunhofer-Gesellschaft · Oberhausen

ThesisGerman needed: not said

Still open on 3 Nov

You apply on the company's own website.

Key facts

Pay: Paid by a set pay agreement
Duration: Until your thesis is done
Subject you study: Computer Science, Data Science, Physics, Mechanical Engineering

You set up a laboratory measuring system with camera technology and lighting and optimize it for reproducible capture of surface structures
You create a training dataset of surface images with known abrasiveness or abrasiveness to be determined during the work
You develop AI-supported image analysis and cluster the surfaces by characteristic wear features (supported by the Fraunhofer Institute for Industrial Mathematics ITWM)

Ongoing master's studies in computer science, data science, physics, mechanical engineering or similar
Programming skills in Python
Basic knowledge of machine learning and image processing
Ideally first experience with CNNs/Vision Transformers, clustering methods and basic knowledge of optical measurement/lighting technology
Good English skills are an advantage

Teamwork on equal terms: An open-minded team in which you can contribute your own ideas. New Work, diversity and inclusion and cooperation are central parts of our culture.
Theory meets practice: The chance to combine your knowledge from your studies with practical experience at the interface between business and science.
Flex Work: Your studies have priority, we offer flexible working hours that adapt to your daily study life.
Students@UMSICHT: Comprehensive onboarding, good support and networking opportunities as well as varied support for your career development through training and talks.
Health & well-being: Health offers for a good balance in everyday life.

You set up a laboratory measuring system with camera technology and lighting and optimize it for reproducible capture of surface structures
You create a training dataset of surface images with known abrasiveness or abrasiveness to be determined during the work
You develop AI-supported image analysis and cluster the surfaces by characteristic wear features (supported by the Fraunhofer Institute for Industrial Mathematics ITWM)

Ongoing master's studies in computer science, data science, physics, mechanical engineering or similar
Programming skills in Python
Basic knowledge of machine learning and image processing
Ideally first experience with CNNs/Vision Transformers, clustering methods and basic knowledge of optical measurement/lighting technology
Good English skills are an advantage

Teamwork on equal terms: An open-minded team in which you can contribute your own ideas. New Work, diversity and inclusion and cooperation are central parts of our culture.
Theory meets practice: The chance to combine your knowledge from your studies with practical experience at the interface between business and science.
Flex Work: Your studies have priority, we offer flexible working hours that adapt to your daily study life.
Students@UMSICHT: Comprehensive onboarding, good support and networking opportunities as well as varied support for your career development through training and talks.
Health & well-being: Health offers for a good balance in everyday life.