Image data filtering and automatic detection of damages within asphalt with the help of ground-penetrating radar (GPR) and machine learning methods

Image data filtering and automatic detection of damages within asphalt with the help of ground-penetrating radar (GPR) and machine learning methods

ZHANG, ZIFAN (TU Delft Civil Engineering and Geosciences; TU Delft Geoscience and Engineering)

Slob, E.C. (mentor)
van Beuningen, Ruud (mentor)

Delft University of Technology
ETH Zürich
RWTH Aachen University

Applied Geophysics | IDEA League

2022-08-26

Damages within asphalt have been interesting phenomena in asphalt engineering, the detection of which is significant for maintenance of road sections. This project focuses on cracks and delaminations. An attempt was made to filter radar image data with a method based on a VNA-antenna-multilayered system model as well as the data from two specific measurements, aiming at better visualizing cracks as well as other features in radar image, and the results were checked and analysed. This part of work has provided an application of the aforementioned method of radar image data filtering as well as the points worth noticing and avoiding when making this application.
For delaminations, machine learning algorithms, first the EM algorithm and then the YOLO v3 algorithm, were used as an attempt to highlight and detect them. Though the results still need improving, it is still valuable that the workload for human intervention can be alleviated with the help of these algorithms and that better performance can be expected based on current work, with the increasing amount of data with high quality achieved in the future.

asphalt damage
GPR
data filtering
machine learning

http://resolver.tudelft.nl/uuid:bd56f449-8f2e-47c3-a3f7-773da2b5c286

Student theses

master thesis

© 2022 ZIFAN ZHANG