Měření vzdáleností pomocí vícesnímkové fotogrammetrie

Abstract

This bachelor thesis deals with the design and implementation of a desktop application for measuring distances in an image using multi-frame photogrammetry. The application allows the user to manually select corresponding points in rectified stereo images, then perform distance calculation using triangulation, both within a single image and across multiple views. An important part of the solution is also the implementation of camera calibration using multiple calibration patterns to determine internal camera parameters. The application is built on the OpenCV library for image manipulation and PyQt for creating the graphical user interface. The paper concludes with an experimental verification of the accuracy of the measurements and a comparison with reference values.