prikaz prve stranice dokumenta Semantička segmentacija slika korištenjem dubokih modela
No public access
master's thesis
Semantička segmentacija slika korištenjem dubokih modela
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. urn:nbn:hr:168:882144
Ćosić-Dragan, Karla
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ćosić Dragan, K. (2024). Semantička segmentacija slika korištenjem dubokih modela (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:882144

Ćosić Dragan, Karla. "Semantička segmentacija slika korištenjem dubokih modela." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:882144

Ćosić Dragan, Karla. "Semantička segmentacija slika korištenjem dubokih modela." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:882144

Ćosić Dragan, K. (2024). 'Semantička segmentacija slika korištenjem dubokih modela', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 28 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:882144

Ćosić Dragan K. Semantička segmentacija slika korištenjem dubokih modela [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2024 December 28] Available at: https://urn.nsk.hr/urn:nbn:hr:168:882144

K. Ćosić Dragan, "Semantička segmentacija slika korištenjem dubokih modela", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:882144

Metadata
TitleSemantička segmentacija slika korištenjem dubokih modela
Title (english)Semantic image segmentation using deep models
AuthorKarla Ćosić-Dragan
MentorZoran Kalafatić (mentor)
Committee memberZoran Kalafatić (predsjednik povjerenstva)
Committee memberTomislav Hrkać (član povjerenstva)
Committee memberVladimir Čeperić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2024-02-26, Croatia
Abstract
Semantička segmentacija u kontekstu računalnog vida provodi dodjeljivanje klase objekta svakom pikselu slike u ovisnosti kojem objektu taj piksel pripada. Za taj se zadatak većinom koriste koder-dekoder arhitekture koje kao okosnicu obično koriste neke od standardnih arhitektura dubokog učenja. U ovom je radu predstavljen pregled nekih od standardnih arhitektura dubokog učenja, zatim pregled koder-dekoder arhitektura i metrika korištenih za semantičku segmentaciju. Za eksperimente je odabrana SwiftNet arhitektura uz programski okvir Pytorch Lightning i skupovi podataka Cityscapes i ACDC. Postignuti su očekivani rezultati i provedene su predikcije na validacijskim skupovima
Abstract (english)
Semantic segmentation in the context of computer vision assigns an object class to each pixel on the image depending on which object that pixel belongs to. The encoder-decoder architectures are mostly used for this task along with some of the standard deep learning architectures used as a backbone. This master thesis presents an overview of some standard deep architectures, followed by an overview of encoder-decoder architectures and metrics used for semantic segmentation. SwiftNet architecture with Pytorch Lightning framework were used for the experiments along with Cityscapes and ACDC datasets. Expected results were achieved and predictions were made on validation sets.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:882144
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 on2024-03-28 07:45:06