Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja

Đuranović, Daniel

prikaz prve stranice dokumenta Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja

Download
PDF 5.78 MB

master's thesis

Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja

Rijeka: University of Rijeka, Faculty of Engineering, 2022. urn:nbn:hr:190:009642

Đuranović, Daniel

University of Rijeka
Faculty of Engineering
Department of Automation and Electronics
Section of Electronics, Robotics and Automation

Cite this document

APA 6th Edition

Đuranović, D. (2022). Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:009642

MLA 8th Edition

Đuranović, Daniel. "Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja." Master's thesis, University of Rijeka, Faculty of Engineering, 2022. https://urn.nsk.hr/urn:nbn:hr:190:009642

Chicago 17th Edition

Đuranović, Daniel. "Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja." Master's thesis, University of Rijeka, Faculty of Engineering, 2022. https://urn.nsk.hr/urn:nbn:hr:190:009642

Harvard

Đuranović, D. (2022). 'Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 18 March 2025, https://urn.nsk.hr/urn:nbn:hr:190:009642

Vancouver

Đuranović D. Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2022 [cited 2025 March 18] Available at: https://urn.nsk.hr/urn:nbn:hr:190:009642

IEEE

D. Đuranović, "Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:190:009642

Cite this item: https://urn.nsk.hr/urn:nbn:hr:190:009642

Please login to the repository to save this object to your list.

Metadata

Title	Detekcija geografskih karakteristika Venere korištenjem algoritama strojnog učenja
Title (english)	Detection of Venus geographic characteristics using machine learning algorithms
Author	Daniel Đuranović
Mentor	Zlatan Car (mentor)
Committee member	Saša Vlahinić (predsjednik povjerenstva)
Committee member	Zlatan Car (član povjerenstva)
Committee member	Ivan Volarić (član povjerenstva)
Granter	University of Rijeka Faculty of Engineering (Department of Automation and Electronics) (Section of Electronics, Robotics and Automation) Rijeka
Defense date and country	2022-09-20, Croatia
Scientific / art field, discipline and subdiscipline	TECHNICAL SCIENCES Electrical Engineering Automation and Robotics
Abstract	Ovim radom opisana je realizacija sustava za detekciju vulkana sa satelitskih snimka planetarne površine Venere. U prvome dijelu objašnjeni su osnovni princip rada i struktura YOLO algoritma koji je korišten kao metoda detekcije objekata. Zatim su prezentirane metode pripreme i obrade Magellan seta podataka u svrhu učenja neuronske mreže. Nakon toga su prezentirani problemi s kojima se suočilo zbog relativno malog seta podataka, te su objašnjena rješenja s kojima se uspjelo doći do zadovoljavajućih rezultata modela. Na samome kraju predstavljena su idejna rješenja za buduća istraživanja u svrhu poboljšanja preciznosti modela kod detekcije jako malih objekata.
Abstract (english)	This work describes the implementation of a volcano detection system with a satellite image of the planetary surface of Venus. In the first part, the basic working principle and structure of the YOLO algorithm, which is used as an object detection method, are explained. Then the methods of preparation and processing of the Magellan dataset for the purpose of neural network learning are presented. After that, the problems faced due to a relatively small set of data were presented, and the solutions with which it was possible to achieve satisfactory model results were explained. At the very end, conceptual solutions for future research are presented in order to improve the precision of the model for detection of very small objects.
Keywords
Keywords (english)
Language	croatian
URN:NBN	urn:nbn:hr:190:009642
Study programme	Title: Graduate University Study of Electrical Engineering Study programme type: university Study level: graduate Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike (magistar/magistra inženjer/inženjerka elektrotehnike)
Type of resource	Text
File origin	Born digital
Access conditions	Open access
Terms of use
Repository	Repository of the University of Rijeka, Faculty of Engineering
Created on	2022-09-19 15:35:32