Road fracture identification using image processing

OData support
Supervisor:
Dr. Csorba Kristóf
Department of Automation and Applied Informatics

Picture processing is a quickly developing, really popular science nowadays with a lot of unexploited opportunities. It’s results can be used in a lot of different areas, such as safety, pharmaceutical - and construction industry and different manufacturing processes. The wide variety of usability and the new scientific breakthroughs were the reasons for me to start working on this topic.

Detecting and analysing asphalt fractures is such an image processing area which handles a problem that is important for most of us. At the present, it is not a common practice to automatically detect these fractures, but I think, - with regard of the growing popularity of smart cars – in the future automatic error detection based on similar methods may become widespread.

OpenCV (Open Source Computer Vision Library) is a software library, developed for picture processing and machine learning purposes. It is really useful, hight level tool for these type of topics, especially paired with the cv4sensorhub framework, which is a developed in the university and makes interaction with the user really effective. With the tools mentioned above I was managed to develop an application which is able to detect fractures and sort them by type, all through a user-friendly interface.

I think these results could mean a stable base for future development in this topic, and the user friendly interface with the picture processing algorythms are really effective tools for detecting asphalt fractures.

Downloads

Please sign in to download the files of this thesis.