Vizijski sustav za praćenje objekata aktuiran servo motorom

undergraduate thesis

• Title (english): Vision system for tracking objects actuated by servo motor
• Author: Dominik Levanić
• Mentor: Bojan Jerbić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2019-02-28, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Zadatak ovog završnog rada je projektirati i integrirati računalni vizijski sustav za lokalizaciju i praćenje objekata (eng. Object Localization and Tracking) prema nekoliko algoritama, a koji se sastoji od kamere, upravljačke jedinice Raspberry Pi te servo motora. Kamerom snimljen video zapis se obrađuje i u realnom vremenu prikazuje na zaslonu računala. Računalo je spojeno s upravljačkom jedinicom korištenom za upravljanje servo motorom koji pokreće kameru i u realnom vremenu je usmjerava prema određenom objektu. Na početku rada će se razjasniti osnovni pojmovi vezani uz područje vizijskih sustava te prednosti i nedostaci njihove uporabe. Zatim će biti opisane korištene komponente sustava, kao i razvijeni algoritmi korišteni za lokalizaciju i praćenje objekata. U razvoju algoritama korištena je računalna knjižnica otvorenog koda OpenCV. Računalni program je razvijen u programskom jeziku Python. Naposljetku će se evaluirati izvedba navedenog vizijskog sustava te dati prijedlog njegove moguće primjene.

Abstract (english)

The goal of this final project is to design and integrate a computer vision system for object localization and tracking according to a couple of algorithms, and which consists of a camera, a control unit Raspberry Pi and a servomotor. Video record captured by the camera is processed and in the real-time reproduced on the computer screen. Computer si connected with the control unit used for controlling servomotor which starts the camera and directs it in the real-time to the specified object. At the beginning of the work, the basic terms about computer vision will be clarified, as will their pros and cons as well. Then the used system components will be described, as will developed algorithms used for object localization and tracking. In the development of algorithms, the open-source library OpenCV is used. At last, the evaluation and the proposal of possible application of the cited vision system will be given.

• Keywords: vizijski sustav; Raspberry Pi; servo motor; OpenCV knjižnica
• Keywords (english): vision system; Raspberry Pi; servomotor; OpenCV library
• Language: croatian
• URN:NBN: urn:nbn:hr:235:963124
• 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: 2019-05-23 00:22:55