ETRO VUB
About ETRO  |  News  |  Events  |  Vacancies  |  Contact  
Home Research Education Industry Publications About ETRO

Master theses

Current and past ideas and concepts for Master Theses.

Semi-automated as-built verification of railway infrastructure using drone imagery

Subject

The scope of this thesis can be more focused on certain aspects in agreement with the student

Kind of work

The thesis student will attempt to validate the supplied Topography measurements with given orthophotos.
The student will attempt to detect a small set of common railway infrastructure elements such as rails, traverse, signals using morphological computer vision operations (eg. non-AI driven).
He will develop new algorithms using well known classical machine vision approaches (hough transform, edge detection,..) together with the aid of existing measured topography and optionally manual user input. In this work the existing vector data will be either: validated, updated or deleted I accordance to the situation captured on the orthographic imagery.

Framework of the Thesis

The main objectives of this thesis are:

Research and Selection of Algorithms & Libraries – Investigate suitable computer vision techniques, such as edge detection and Hough transform, to detect railway infrastructure elements. Evaluate existing open-source libraries and frameworks that support classical machine vision.

Development of Morphological Computer Vision Methods – Implement and optimize non-AI-based image processing techniques to detect railway components (e.g., rails, traverses, signals) in orthophotos while leveraging topographic data for validation.

Integration of Topography Measurements – Utilize existing topography data to enhance detection accuracy, ensuring consistency between detected elements in orthophotos and measured ground data.

Validation and Updating of Existing Vector Data – Compare detected objects with pre-existing vector datasets to validate, update, or remove outdated elements based on real-world conditions observed in the orthophotos.

Number of Students

1

Expected Student Profile

Basic understanding of railway infrastructure and components (e.g., signals, switches, panels).

Knowledge of UAV operations and flight planning for data acquisition.

Programming skills in Python for algorithm development and optimization. (Must have knowledge of python)

Analytical skills for data processing, accuracy assessment, and system validation.

Promotor

Prof. Dr. Ir. Adrian Munteanu

+32 (0)2 629 1684

acmuntea@etrovub.be

more info

Supervisor

Mr. Mohammad Ali Tahouri

+32 (0)2 629 2930

mtahouri@etrovub.be

more info

- Contact person

- IRIS

- AVSP

- LAMI

- Contact person

- Thesis proposals

- ETRO Courses

- Contact person

- Spin-offs

- Know How

- Journals

- Conferences

- Books

- Vacancies

- News

- Events

- Press

Contact

ETRO Department

Tel: +32 2 629 29 30

©2025 • Vrije Universiteit Brussel • ETRO Dept. • Pleinlaan 2 • 1050 Brussels • Tel: +32 2 629 2930 (secretariat) • Fax: +32 2 629 2883 • WebmasterDisclaimer

R&D groups & themes:
IRIS GroupLAMI GroupAVSP Group
Interdisciplinary researchInfrastructure for scientific and / or industrial research
ETRO Publications:
IRIS Group - PublicationsLAMI Group - PublicationsAVSP Group - Publications
Industry
ETRO Publications:
JournalConference   Book
ReportLaymenPhD Thesis
    About ETRO
    Education Activities:
    ETRO CoursesThesis Proposals
      Infrastructure for education:Infrastructure for research & education:Previous year's student projects