prikaz prve stranice dokumenta Ekstrakcija prometnica iz satelitskih slika
Access restricted to students and staff of home institution
master's thesis
Ekstrakcija prometnica iz satelitskih slika
2020. urn:nbn:hr:190:895684
Gašparović, Boris
University of Rijeka
Faculty of Engineering
Department of Automation and Electronics
Section of Signals and Systems

Cite this document

Gašparović, B. (2020). Ekstrakcija prometnica iz satelitskih slika (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:895684

Gašparović, Boris. "Ekstrakcija prometnica iz satelitskih slika." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:895684

Gašparović, Boris. "Ekstrakcija prometnica iz satelitskih slika." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:895684

Gašparović, B. (2020). 'Ekstrakcija prometnica iz satelitskih slika', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 08 January 2025, https://urn.nsk.hr/urn:nbn:hr:190:895684

Gašparović B. Ekstrakcija prometnica iz satelitskih slika [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2020 [cited 2025 January 08] Available at: https://urn.nsk.hr/urn:nbn:hr:190:895684

B. Gašparović, "Ekstrakcija prometnica iz satelitskih slika", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:190:895684

Please login to the repository to save this object to your list.
Metadata
TitleEkstrakcija prometnica iz satelitskih slika
Title (english)Road Extraction from Satellite Images
AuthorBoris Gašparović
MentorJonatan Lerga (mentor)
Committee memberSandi Ljubić (predsjednik povjerenstva)
Committee memberGoran Mauša (član povjerenstva)
Committee memberJonatan Lerga (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Automation and Electronics)
(Section of Signals and Systems)
Rijeka
Defense date and country2020-11-20, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu prikazane su i uspoređene metode ekstrakcije prometnica iz satelitske snimke. Ukupno su uspoređena četiri modela ekstrakcije ceste iz satelitske snimke; dva open source modela koji se temelje samo na grafičkim značajkama, model predložen u ovom radu pod nazivom modificirani algoritam koji se temelji na grafičkim značajkama te pristup ekstrakciji prometnica strojnim učenjem. Dokazali smo da je predloženi pristup modificiranim algoritmom najuspješniji od modela koji se temelje samo na grafičkim značajkama. Zaključeno je da smo korištenjem optimizacijskih metoda nad modelom koji koristi strojno učenje u mogućnosti bolje ekstrahirati ceste iz satelitskih snimaka u usporedbi s metodom koja koristi modificirani algoritam.
Abstract (english)
This thesis presents and compares methods for road extraction from satellite imagery. A total of four road extraction models from satellite images were compared; two open-source models based only on graphical features, the model proposed in this paper called a modified algorithm (also based on graphical features), and a model for extracting roads based on machine learning. We demonstrated that the proposed modified algorithm is the most successful method among these based only on graphical features. We concluded that by using optimization methods over model based on machine learning, we could better extract roads from satellite images compared to the method that uses a modified algorithm.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:895684
Study programmeTitle: Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2020-12-29 10:26:46