Analýza objektov z iducého vlaku

Abstract

The aim of the work was to analyze the important objects located around the tracks from the images that were taken from the train's point of view. The application was developed using Python libraries. The text of this thesis is divided into several main sections. In the theoretical section, the main concepts behind the operation of the different image segmentation approaches are explained. The practical part concentrates on the creation of segmentation of different objects around the track using these methods. The methods used are among those based on deep learning principles.