prikaz prve stranice dokumenta Vrednovanje modela SwiftNet za semantičku segmentaciju
No public access
master's thesis
Vrednovanje modela SwiftNet za semantičku segmentaciju
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:887003
Krivošić, Matija
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Krivošić, M. (2020). Vrednovanje modela SwiftNet za semantičku segmentaciju (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:887003

Krivošić, Matija. "Vrednovanje modela SwiftNet za semantičku segmentaciju." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:887003

Krivošić, Matija. "Vrednovanje modela SwiftNet za semantičku segmentaciju." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:887003

Krivošić, M. (2020). 'Vrednovanje modela SwiftNet za semantičku segmentaciju', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:887003

Krivošić M. Vrednovanje modela SwiftNet za semantičku segmentaciju [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 December 26] Available at: https://urn.nsk.hr/urn:nbn:hr:168:887003

M. Krivošić, "Vrednovanje modela SwiftNet za semantičku segmentaciju", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:887003

Metadata
TitleVrednovanje modela SwiftNet za semantičku segmentaciju
Title (english)Evaluation of the SwiftNet model for semantic segmentation
AuthorMatija Krivošić
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberSlobodan Ribarić (član povjerenstva)
Committee memberVlado Glavinić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Semantička segmentacije je težak problem računalnog vida. Zbog svoje primjene u brojnim područjima kao što su automobilska industrija i robotika važno je da se segmentacija izvršava s visokom točnošću i u stvarnom vremenu. Zadatak ovog rada je treniranje i evaluiranje SwiftNet model. Eksperimenti su provedeni na CamVid i Cityscapes skupovima podataka. SwiftNet model je pokazao vrlo dobre rezultate. Postignuti rezultati su prikazani vizualno i numerički.
Abstract (english)
Semantic segmentation is a demanding computer vision problem. Due to its application in a number of areas such as the automotive industry and robotics, it is important that segmentation is performed with high accuracy and in real time. The task of this paper is to train and evaluate the SwiftNet model. Experiments are performed on CamVid and Cityscapes datasets. The SwiftNet model showed very good results. The achieved results are presented visually and numerically.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:887003
Study programmeTitle: Computing
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 conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 10:13:57