prikaz prve stranice dokumenta Praćenje kontura pomoću robota
  Download
PDF 1.63 MB
undergraduate thesis
Praćenje kontura pomoću robota
Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2015. urn:nbn:hr:235:244314
Grgić, Bruno
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Institutional repository: Repository of Faculty of Mechanical Engineering and Naval Architecture University of Zagreb

Cite this document

Grgić, B. (2015). Praćenje kontura pomoću robota (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:244314

Grgić, Bruno. "Praćenje kontura pomoću robota." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2015. https://urn.nsk.hr/urn:nbn:hr:235:244314

Grgić, Bruno. "Praćenje kontura pomoću robota." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2015. https://urn.nsk.hr/urn:nbn:hr:235:244314

Grgić, B. (2015). 'Praćenje kontura pomoću robota', Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 18 December 2024, https://urn.nsk.hr/urn:nbn:hr:235:244314

Grgić B. Praćenje kontura pomoću robota [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2015 [cited 2024 December 18] Available at: https://urn.nsk.hr/urn:nbn:hr:235:244314

B. Grgić, "Praćenje kontura pomoću robota", Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2015. Available at: https://urn.nsk.hr/urn:nbn:hr:235:244314

Metadata
TitlePraćenje kontura pomoću robota
Title (english)Robotic contour following
AuthorBruno Grgić
MentorBojan Jerbić (mentor)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2015-03-03, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
Cilj ovog rada bio je razviti vizijski sustav koji prepoznaje konture željenog predmeta. Uvod daje kratki opis potrebe za automatizacijom industrijskog brušenja i prednosti koje vizijski sustav pridonosi takvim procesima. U prvom poglavlju razvijen je vizijski sustav baziran na Canny algoritmu i čvorovima aproksimacijskih funkcija. Prije dobivanja točaka kontura, primjenjeni su medijanski filter i piramidno skaliranje za dodatno isticanje obrisa objekata na slikama. Nakon dobivanja kontura predmeta, koristeći njihovo hijerarhijsko stablo uspjeva se pristupiti željenim konturama, te se postavljaju razni uvjeti provjere kako bi se osigurala visoka točnost prepoznavanja željenih obrisa. Vizijski sustav može se primijeniti na predmetima različitih oblika, dimenzija i orijentacije. Vizijski i upravljački algoritam razvijani su u programskom jeziku C++. Korištena je knjižnica OpenCV u Microsoft Visual Studio 2010 programskom okruženju. Drugo poglavlje opisuje transformaciju koordinatnog sustava kamere i koordinatnog sustava robota u jednu točku radne površine. Ishodišta vizijskog sustava i koodinatnog sustava robota moraju biti precizno usklađena ako želimo točno praćenje kontura predmeta prihvatnicom robota. Obrađen je upravljački algoritam koji komunicira podatke o tim konturama robotu u obliku točaka. Točke pretvorene iz piksela u milimetre preuzima robot Ethernet komunikacijom. Programski jezik robota je Karel. Proces simulira postupak industrijskog brušenja predmeta na proizvodnoj liniji.
Abstract (english)
The objective of this paper was to develop a computer vision algorithm that detects contours of the targeted objects. Introduction provides a short explanation of the needs for automatization of industrial grinding process and advantages that computer vision system provides to such processes. In the first chapter a computer vision algorithm is developed based on Canny algorithm and approximation function vertices. Before acquiring contour points, median filter and pyramid scaling are used for improved edge recognition. After acquiring the object's contours, successful targeting of the specified contours is achieved using their hierarchy tree and application of various verification criteria to ensure high accuracy of targeted edge recognition. Computer vision and control algorithm are developed in C++. OpenCV library is used in Microsoft Visual Studio 2010 IDE. Second chapter describes transformation of camera's and robot's coordinate systems into a single point on work area. Origins of computer vision's and robot's coordinate systems need to be precisely alligned if we want accurate contour following with robot's arm. Control algorithm that communicates data about those contours in form of points is elaborated. Points transformed from pixels to milimeters are acquired by robot via Ethernet communication. Robot's programming language is Karel. The method simulates industrial brushing process on production line.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:235:244314
Study programmeTitle: 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 resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2019-05-22 13:13:20