Vizijski sustav za praćenje objekata prema obliku i boji

undergraduate thesis

• Title (english): A vision system for tracking objects by shape and color
• Author: Tibor Vranić
• Mentor: Mladen Crneković (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2023-09-28, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Osnovni uvjet inteligentnog ponašanja mobilnih robota je spoznaja o prostoru u kojem se kreću
te sposobnost klasifikacije situacije u svrhu izvršavanja zadatka. Fokus rada će stoga bit
postavljen na konkretnu implementaciju računalnog i strojnog vida u Pythonu.
Korištenjem bogatih biblioteka OpenCV i NumPy, Python nam omogućuje da emuliramo
ljudski vizualni sustav. Ovime se otvara mogućnost pretvaranja vizualnih informacija u korisne
uvide i unapređenja u područjima poput robotike, medicine i automatizacije.
Uz to, biti će objašnjen način na koji Python olakšava izradu korisničkog sučelja pomoću
Tkinter biblioteke, omogućujući čak i manje iskusnim programerima da razviju intuitivna
rješenja u svojim aplikacijama.
Koristeći prikladne metode i algoritme iz područja strojnog vida izrađena je programska
aplikacija za detekciju objekata temeljem boje i oblika. Također je analizirana funkcionalnost
ovakvog sustava u različitim uvjetima te ponuđeno rješenje na temelju kalibracije boja.

Abstract (english)

The fundamental requirement for the intelligent behavior of mobile robots is their
understanding of the space they move in and their ability to classify situations for the purpose
of task execution. Therefore, the focus of this work will be on the concrete implementation of
computer and machine vision in Python.
By using rich libraries like OpenCV and NumPy, Python allows us to emulate the human visual
system. This opens up the possibility of transforming visual information into valuable insights
and improvements in areas such as robotics, medicine, and automation.
Furthermore, the way Python facilitates the creation of user interfaces through the Tkinter
library will be explained. This enables even less experienced programmers to develop intuitive
solutions in their applications.
Using appropriate methods and algorithms from the field of machine vision, a software
application for object detection based on color and shape has been developed. The functionality
of such a system in different conditions has also been analyzed, and a solution based on color
calibration has been proposed.

• Keywords: Računalni vid; strojni vid; robotika; Python; Tkinter; NumPy; OpenCV
• Keywords (english): Computer vision; machine vision; robotics; Python; Tkinter; NumPy; OpenCV
• Language: croatian
• URN:NBN: urn:nbn:hr:235:445382
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2023-09-26 16:25:56