prikaz prve stranice dokumenta Vizualno inercijski navigacijski sustavi
Access restricted to authenticated users
undergraduate thesis
Vizualno inercijski navigacijski sustavi
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:179:142353
Miličević, Mario
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Miličević, M. (2022). Vizualno inercijski navigacijski sustavi (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:142353

Miličević, Mario. "Vizualno inercijski navigacijski sustavi." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:142353

Miličević, Mario. "Vizualno inercijski navigacijski sustavi." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:142353

Miličević, M. (2022). 'Vizualno inercijski navigacijski sustavi', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 29 June 2024, https://urn.nsk.hr/urn:nbn:hr:179:142353

Miličević M. Vizualno inercijski navigacijski sustavi [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 June 29] Available at: https://urn.nsk.hr/urn:nbn:hr:179:142353

M. Miličević, "Vizualno inercijski navigacijski sustavi", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:142353

Metadata
TitleVizualno inercijski navigacijski sustavi
AuthorMario Miličević
MentorMirjana Bonković (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-21, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom završnom radu realizirana je demonstracija sustava VINS-Fusion za vizualno inercijsku simultanu lokalizaciju i mapiranje kao samostalni sustav i u kontekstu područja računalnog vida, objašnjen je proces instalacije programskog paketa i njegovih ovisnosti na Ubuntu platformi, kao i rad sustava na stvarnim eksperimentalnim podacima i njegov učinak na podatke. Objašnjen je koncept kamere, povijest njenog razvoja od izuma do današnje integracije u tehnologiju, i matematički model perspektivne projekcije. Prezentirani su glavni algoritmi koji omogućavaju rad vizualne odometrije koja uz inercijske senzore čini ovaj sustav mogućim: algoritam osam točaka, perspektiva-3-točke, i RANSAC, skupa sa pripadajućim vizualizacijama, MATLAB primjerima i objašnjenjem procesa rada algoritama. Ovaj rad može poslužiti kao uvod u područje vizualno inercijske navigacije, pomoć pri instalaciji VINS-Fusion sustava i demonstracija mogućnosti ROS programskog paketa.
Abstract (english)
In this final thesis, a demonstration of VINS-Fusion, a system for visual inertial simultaneous localization and mapping has been realised as both a standalone system and in context of the computer vision field. The installation process of the software package on Ubuntu operating system and its dependencies has been explained, as well as a demonstration of the system working with real experimental data and its effect on said data. The concept of a camera, the history of its development from its invention all the way to today's integration with technology, as well as the mathematical perspective projection model have been explained. The main algorithms for visual odometry, which in combination with inertial sensors make this system possible: 8-point algorithm, Perspective-3-Point and RANSAC, together with corresponding visualizations, MATLAB examples and their work processes explained. This thesis can be used as an introduction to the field of visual inertial navigation, a help with VINS-Fusion instalation, as well as a demonstration of some of ROS's capabilities.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:142353
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-06-09 10:26:50