prikaz prve stranice dokumenta Učenje dubokih korespondencijskih metrika trojnim gubitkom
No public access
master's thesis
Učenje dubokih korespondencijskih metrika trojnim gubitkom
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:039533
Kostelac, Marin
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Kostelac, M. (2018). Učenje dubokih korespondencijskih metrika trojnim gubitkom (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:039533

Kostelac, Marin. "Učenje dubokih korespondencijskih metrika trojnim gubitkom." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:039533

Kostelac, Marin. "Učenje dubokih korespondencijskih metrika trojnim gubitkom." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:039533

Kostelac, M. (2018). 'Učenje dubokih korespondencijskih metrika trojnim gubitkom', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 01 June 2024, https://urn.nsk.hr/urn:nbn:hr:168:039533

Kostelac M. Učenje dubokih korespondencijskih metrika trojnim gubitkom [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 June 01] Available at: https://urn.nsk.hr/urn:nbn:hr:168:039533

M. Kostelac, "Učenje dubokih korespondencijskih metrika trojnim gubitkom", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:039533

Metadata
TitleUčenje dubokih korespondencijskih metrika trojnim gubitkom
Title (english)Learning deep correspondence metrics with triplet loss
AuthorMarin Kostelac
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberJan Šnajder (član povjerenstva)
Committee memberTomislav Hrkać (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Stereoskopska rekonstrukcija je bitno polje računalnog vida. Najbitniji dio problema je pronalazak korespondentnih piksela u dvjema slikama iste scene. To je moguće ostvariti koristeći korespondencijske metrike. Pri učenju korespondencijskih metrika od velike pomoći je trojni gubitak. Definiranjem odnosa med̄u podacima moguće je naučiti metriku koja olakšava pronalazak korespondentnih piksela. U okviru rada opisan je problem stereoskopske rekonstrukcije i primjena korespondencijskih metrika i trojnog gubitka na njega. Opisan je i testiran model za rješavanje opisanog problema.
Abstract (english)
Stereoscopic reconstruction is an important field in computer vision. The most important part of the problem is finding the corresponding pixels in two images of the same scene. It is possible to achieve that using correspondence metrics. Triplet loss is a big help in training correspondence metrics. By defining the data relations it is possible to train a metric which makes finding corresponding pixels easier. in this thesis, the stereoscopic reconstruction problem is described. Application of correspondence metrics and triplet loss to it are explained. A model for solving the problem is described and tested.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:039533
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 on2019-03-13 21:45:09