Vizualno prepoznavanje i modeliranje radnog prostora mobilnog robota

master's thesis

• Title (english): Visual recognition and modeling of mobile robot working space
• Author: Siniša Španić
• Mentor: Andrej Jokić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2015-12-03, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Ovaj rad načinjen je sa ciljem vizualnog prepoznavanja eMIR robota u njegovom radnom prostoru pomoću kamere montirane iznad radnog prostora. Informacije dobivene vizualno šalju se zatim preko virtualnog komunikacijskog kanala drugoj aplikaciji koja ih zatim prikaže. Glavni i pomoćni program napravljeni se u Qt programskom okruženju i korištenjem biblioteka za računalni vid OpenCV. Glavni program dohvaća slike s kamere montirane iznad radnog prostora, traži eMiR robota u zadanoj boji te iz položaja robota na slici uzima informacije o njegovom položaju koje zatim pretvara u dogovoreni format te šalje preko virtualnog komunikacijskog kanala. Na drugoj strani komunikacijskog kanala pomoćni program prihvaća te informacije i prikazuje ih. Prepoznavanje robota napravljeno je na temelju razlika u njihovoj boji. Testovima je pokazan utjecaj promjene svjetlosnih uvjeta na detekciju objekta. Testiranjem je pokazano da prepoznavanje robota funkcionira u konstantnim svjetlosnim uvjetima za koje se sustav baždari.

Abstract (english)

This work is made with the goal of the visual recognition eMiR mobile robot in his working space with help of the camera mounted above the working space. Information obtained visually are sent over the virtual communication channel to another application that then displays them. Main and auxiliary applications are made in Qt programming environment and with using the library for computer vision OpenCV. Main program receives camera images search eMiR robot and from the position of the robot on the picture calculates its position. Informations obtained are then translated into agreed format and are sent over via virtual communication channel. Auxiliary application reads those information obtained from communication channel and displays them. Visual recognition of the eMiR robot is made on the basis of differences in their color. Tests showed the influence of changing light conditions on the detection of the object. Also tests showed that visual recognition of the eMiR robot works in the constant light conditions for which is calibrated.

• Keywords: vizijski sustav; opencv; kamera; prepoznavanje; eMIR
• Keywords (english): vision system; opencv; camera; recognition; eMIR
• Language: croatian
• URN:NBN: urn:nbn:hr:235:363243
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2019-05-22 15:09:55