Register now After registration you will be able to apply for this opportunity online.
Visual condition monitoring of Railway retaining walls with machine learning
This project is part of a collaboration between the IMOS lab and Matterhorn Gotthard Bahn, a railway company operating in the Swiss Alps. The student will work on developing computer vision algorithms for automated visual inspection of retaining walls around railway tracks. Retaining (or supporting) walls are crucial infrastructure elements responsible for maintaining the structural integrity of terrains around railway tracks and ensure safe operation. They are subject to wear and damages including cracks, concrete cancer (i.e., alkali–silica reaction), displacements, erosion and water infiltration. Images of retaining walls have already been collected and labels are available. The goal will be to design algorithms to estimate the condition of a wall, with a focus on robustness, transfer learning, and explainability (XAI).
Keywords: Railway, Structural Health Monitoring, Computer Vision, Machine Learning, Transfer Learning, Domain Adaptation, XAI
The project will include following tasks:
• Develop and evaluate algorithms to estimate the condition of retaining walls from images collected
either from a measuring wagon or from a flying drone (see Figure 1).
• Ground-truth labels are available in the form of human inspection reports.
• Study the evolution of infrastructure condition over time.
• Explore transfer learning between publicly available datasets, wagon, and drone modalities.
• Leverage explainable AI (XAI) tools to explain model predictions and obtain more finegrained
outputs such as precise localization of the damages.
Requirements:
• Motivation to work on machine learning applied to civil engineering and transportation.
• Proficiency in at least a programming language and familiarity with numerical, image processing
and machine learning libraries (e.g., PyTorch, OpenCV, etc.).
• Dedication to write high-quality code and learn good development practices.
• Good communication skills and the ability to collaborate with others.
• Currently enrolled as a Masters student.
The project will include following tasks:
• Develop and evaluate algorithms to estimate the condition of retaining walls from images collected either from a measuring wagon or from a flying drone (see Figure 1).
• Ground-truth labels are available in the form of human inspection reports.
• Study the evolution of infrastructure condition over time.
• Explore transfer learning between publicly available datasets, wagon, and drone modalities.
• Leverage explainable AI (XAI) tools to explain model predictions and obtain more finegrained outputs such as precise localization of the damages.
Requirements:
• Motivation to work on machine learning applied to civil engineering and transportation.
• Proficiency in at least a programming language and familiarity with numerical, image processing and machine learning libraries (e.g., PyTorch, OpenCV, etc.).
• Dedication to write high-quality code and learn good development practices.
• Good communication skills and the ability to collaborate with others.
• Currently enrolled as a Masters student.
Developing computer vision algorithms for automated visual inspection of retaining walls around railway tracks.
Developing computer vision algorithms for automated visual inspection of retaining walls around railway tracks.
Dr. Florent Forest – florent.forest@epfl.ch
Prof. Dr. Olga Fink – olga.fink@epfl.ch