prikaz prve stranice dokumenta Segmentacija plovila iz satelitskih snimaka
  Download
PDF 3.51 MB
master's thesis
Segmentacija plovila iz satelitskih snimaka
Rijeka: University of Rijeka, Faculty of Engineering, 2022. urn:nbn:hr:190:355397
Paladin, Luka
University of Rijeka
Faculty of Engineering
Department of Automation and Electronics
Section of Electronics, Robotics and Automation

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Paladin, L. (2022). Segmentacija plovila iz satelitskih snimaka (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:355397

Paladin, Luka. "Segmentacija plovila iz satelitskih snimaka." Master's thesis, University of Rijeka, Faculty of Engineering, 2022. https://urn.nsk.hr/urn:nbn:hr:190:355397

Paladin, Luka. "Segmentacija plovila iz satelitskih snimaka." Master's thesis, University of Rijeka, Faculty of Engineering, 2022. https://urn.nsk.hr/urn:nbn:hr:190:355397

Paladin, L. (2022). 'Segmentacija plovila iz satelitskih snimaka', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 13 June 2024, https://urn.nsk.hr/urn:nbn:hr:190:355397

Paladin L. Segmentacija plovila iz satelitskih snimaka [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2022 [cited 2024 June 13] Available at: https://urn.nsk.hr/urn:nbn:hr:190:355397

L. Paladin, "Segmentacija plovila iz satelitskih snimaka", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:190:355397

Metadata
TitleSegmentacija plovila iz satelitskih snimaka
Title (english)Segmentation of vessels from stellite images
AuthorLuka Paladin
MentorZlatan Car (mentor)
Committee memberNino Stojković (predsjednik povjerenstva)
Committee memberZlatan Car (član povjerenstva)
Committee memberDario Matika (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Automation and Electronics)
(Section of Electronics, Robotics and Automation)
Rijeka
Defense date and country2022-07-20, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
U ovom se diplomskom radu predstavio zadatak segmentacije plovnih objekata iz satelitskih snimaka. Segmentacija slike je proces razvrstavanja svakog piksela na slici određenoj klasi. U primjeru ovog rada potrebno je bilo predstaviti i realizirati metode segmentiranja plovnih objekata od ostatka slike. Za početak je u širem smislu pojašnjena segmentacija i njezine primjene u stvarnom svijetu. Nakon toga, predstavljen je pregled dosadašnjeg razvoja od matematičkih metoda raznih kompleksnosti do metoda temeljenih na umjetnim neuronskim mrežama. Sljedeće je predstavljena segmentacija u užem smislu segmentacije objekata iz satelitskih snimaka. Završno je kreiran opsežan i kvalitetan skup slikovnih podataka koji je omogućio treniranje i usporedbu FCN, PSPNet, U-Net i Segnet metoda. Danjim ispitivanjem i prilagodbom raznih parametara primjenom U-Net i Segnet metoda postižu se odlični rezultati.
Abstract (english)
In this graduate thesis the task of segmentation of sea vessels from satellite imagery is presented. Image segmentation is the process of sorting each pixel in an image to a specific class. In the example of this work, it was necessary to present and achieve the methods of segmenting sea vessels from the rest of the image. To begin with, segmentation and its applications in the real world are explained in a broader sense. After that, an overview of the development so far from mathematical methods of various complexities to methods based on artificial neural networks was presented. Next, segmentation is presented in the narrow sense of segmentation of objects from satellite imagery. Finally, an extensive and high-quality set of imaging data was created that enabled the training and comparison of FCN, PSPNet, U-Net and Segnet methods. By examining and adjusting various parameters, excellent results are achieved using U-Net and Segnet methods.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:355397
Study programmeTitle: 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 resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2022-07-14 18:05:40