Image recognition of traffic irregularities

OData support
Supervisor:
Dr. Max Gyula
Department of Automation and Applied Informatics

The aim of my thesis is to demonstrate the possibilities of recognizing traffic irregularities by machine vision. This can be considered as a current issue, as the number of cars on the road is growing and the number of accidents is increasing. In order to decrease the number of accidents, first we have to detect the traffic irregularities. Statistics have shown that the main cause of traffic accidents is related to traffic violations. Besides various driving assistance systems, it is essential to be able to identify and record any irregularities and take appropriate steps to help smooth the traffic flow and encourage drivers to comply with the rules. The latter can also result in reduced number of accidents. To resolve my target I used Microsoft Visual Studio (2015) and the newest OpenCV version (3.3.0), which includes hundreds of imaging, image processing and visualization features. At the end of my thesis I also discussed the acquired experience as well as some possibilities for future development.

Downloads

Please sign in to download the files of this thesis.