prikaz prve stranice dokumenta Semantička segmentacija primjeraka korištenjem dubokih konvolucijskih modela
No public access
master's thesis
Semantička segmentacija primjeraka korištenjem dubokih konvolucijskih modela
2020. urn:nbn:hr:168:836914
Prester, Dominik
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Prester, D. (2020). Semantička segmentacija primjeraka korištenjem dubokih konvolucijskih modela (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:836914

Prester, Dominik. "Semantička segmentacija primjeraka korištenjem dubokih konvolucijskih modela." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:836914

Prester, Dominik. "Semantička segmentacija primjeraka korištenjem dubokih konvolucijskih modela." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:836914

Prester, D. (2020). 'Semantička segmentacija primjeraka korištenjem dubokih konvolucijskih modela', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 01 October 2024, https://urn.nsk.hr/urn:nbn:hr:168:836914

Prester D. Semantička segmentacija primjeraka korištenjem dubokih konvolucijskih modela [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 October 01] Available at: https://urn.nsk.hr/urn:nbn:hr:168:836914

D. Prester, "Semantička segmentacija primjeraka korištenjem dubokih konvolucijskih modela", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:836914

Please login to the repository to save this object to your list.
Metadata
TitleSemantička segmentacija primjeraka korištenjem dubokih konvolucijskih modela
Title (english)Semantic Instance Segmentation Using Deep Convolutional Models
AuthorDominik Prester
MentorZoran Kalafatić (mentor)
Committee memberZoran Kalafatić (predsjednik povjerenstva)
Committee memberTomislav Hrkać (član povjerenstva)
Committee memberSiniša Šegvić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Semantička segmentacija primjeraka jedan je od najsloženijih problema računalnog vida jer obuhvaća probleme detekcije objekata i semantičke segmentacije. Nudi se opis zadanog problema, te pregled umjetnih neuronskih mreža koje se mogu koristiti pri rješavanju istih. U okviru rada oblikovana je vlastita implementacija po uzoru na istražene ideje te je evaluirana na javno dostupnom skupu podataka.
Abstract (english)
Instance segmentation is one of the more complicated tasks of computer vision as it encompasses the tasks of object detection and semantic segmentation. An overview of instance segmentation task is given, along with the examination of artificial neural networks that can be used to solve it. An implementation of one such network has been written and tested on a publicly available dataset.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:836914
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 13:34:14