prikaz prve stranice dokumenta Spajanje 3D oblaka točaka na temelju zadanih geometrijskih značajki
Access restricted to authenticated users
master's thesis
Spajanje 3D oblaka točaka na temelju zadanih geometrijskih značajki
2021. urn:nbn:hr:179:340704
Marjanović, Marijo
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Mechanical Engineering and Naval Architecture

Cite this document

Marjanović, M. (2021). Spajanje 3D oblaka točaka na temelju zadanih geometrijskih značajki (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:340704

Marjanović, Marijo. "Spajanje 3D oblaka točaka na temelju zadanih geometrijskih značajki." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:340704

Marjanović, Marijo. "Spajanje 3D oblaka točaka na temelju zadanih geometrijskih značajki." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:340704

Marjanović, M. (2021). 'Spajanje 3D oblaka točaka na temelju zadanih geometrijskih značajki', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 20 April 2024, https://urn.nsk.hr/urn:nbn:hr:179:340704

Marjanović M. Spajanje 3D oblaka točaka na temelju zadanih geometrijskih značajki [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 April 20] Available at: https://urn.nsk.hr/urn:nbn:hr:179:340704

M. Marjanović, "Spajanje 3D oblaka točaka na temelju zadanih geometrijskih značajki", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:340704

Please login to the repository to save this object to your list.
Metadata
TitleSpajanje 3D oblaka točaka na temelju zadanih geometrijskih značajki
Title (english)Merging 3D point clouds based on geometric features
AuthorMarijo Marjanović
MentorMilan Ćurković https://orcid.org/0000-0003-0100-7928 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Mechanical Engineering and Naval Architecture)
Split
Defense date and country2021-09-22, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
Produkt 3D skenera su snimljeni objekti iz stvarnog svijeta i najčešće se nalaze u formatu 3D oblaka točaka. Proces spajanja više 3D oblaka točaka u isti referentni okvir se naziva registracija oblaka točaka. Sama tehnologija pronalazi široku primjenu u raznim industrijama. Rad je podijeljen na teorijski i praktični dio registracije oblaka točaka. U teorijskom dijelu objašnjeni su teorijski principi koje se nalaze u pozadini algoritama za registraciju oblaka točaka. Pozornost rada je usmjerena na ICP algoritam čije su metode rješavanja detaljno objašnjene. Također teorijski su detaljno objašnjeni principi izdvajanja geometrijskih značajki, koje predstavljaju temelj učinkovite registracije oblaka točaka. Opisana je analiza glavnih komponenti (PCA), proračuna normala, zakrivljenost, kut između normala, te PFH i FPFH lokalne značajke koje su se pokazale veoma učinkovite u praktičnom dijelu rada. Cilj praktičnog dijela rada je bilo ispitati teorijska načela u praksi, što je na primjeru dva oblaka točaka i učinjeno. Korišteni programski jezik je Python.
Abstract (english)
Scans from 3D scanners captures real-world objects and they are most often found in the 3D point cloud format. The process of merging multiple 3D point clouds into the same reference frame is called point cloud registration. The technology itself finds wide application in various industries. The paper is divided into theoretical and practical part of point cloud registration. The theoretical part explains the theoretical principles found in the background of the algorithms for point cloud registration. The thesis focuses on the ICP algorithm whose solving methods are explained in detail. Also theoretically explained in detail are the principles of extraction of geometric features, which form the basis of effective registration of point clouds. The analysis of principal components (PCA), calculations of normal, curvature, angle between normal, and PFH and FPFH local characteristics are described, who were very effective in the practical part of the thesis. The aim of the practical part of the thesis was to examine the theoretical principles in practice, which was successfully done on the application of two point clouds. Used programming language is Python.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:340704
Study programmeTitle: Mechanical Engineering; specializations in: Structures and Energy Technology, Computer Aided Design and Engineering, Production Mechanical Engineering
Course: Computer Aided Design and Engineering
Study programme type: university
Study level: graduate
Academic / professional title: Magistar/magistra inženjer/inženjerka strojarstva (Magistar/magistra inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2022-11-04 13:42:22