prikaz prve stranice dokumenta Metoda za procjenu dubine scene temeljena na dubokom učenju
No public access
master's thesis
Metoda za procjenu dubine scene temeljena na dubokom učenju
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:678371
Veić, Matej
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Veić, M. (2022). Metoda za procjenu dubine scene temeljena na dubokom učenju (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:678371

Veić, Matej. "Metoda za procjenu dubine scene temeljena na dubokom učenju." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:678371

Veić, Matej. "Metoda za procjenu dubine scene temeljena na dubokom učenju." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:678371

Veić, M. (2022). 'Metoda za procjenu dubine scene temeljena na dubokom učenju', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 02 October 2024, https://urn.nsk.hr/urn:nbn:hr:168:678371

Veić M. Metoda za procjenu dubine scene temeljena na dubokom učenju [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2024 October 02] Available at: https://urn.nsk.hr/urn:nbn:hr:168:678371

M. Veić, "Metoda za procjenu dubine scene temeljena na dubokom učenju", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:678371

Metadata
TitleMetoda za procjenu dubine scene temeljena na dubokom učenju
Title (english)Scene Depth Estimation Method Based on Deep Learning
AuthorMatej Veić
MentorSven Lončarić (mentor)
Committee memberSven Lončarić (predsjednik povjerenstva)
Committee memberMarko Subašić (član povjerenstva)
Committee memberTomislav Petković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2022-07-07, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Procjena dubine na slici važan je problem računalnog vida koji se obično rješava korištenjem stereo vida. Problem je također moguće riješiti korištenjem samo jedne slike scene. Rad istražuje nekoliko različitih modela za procjenu dubine na temelju jedne slike. To su redom U-Net, ResNet, DenseNet i EfficientNet. Performanse modela ispitane su na dva skupa podataka te su detaljno dokumentirani rezultati.
Abstract (english)
Depth estimation on images is an importan computer vision task. It is usually being solved using stereo cameras. However, it is possible to estimate depth of a scene using only a single image. This thesis explores a couple of common models used for monocular depth estimation. Those are: U-Net, ResNet, DenseNet and EfficientNet. Performances of those models were examined on two separate datasets and results were documented in detail.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:678371
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 on2023-01-14 10:11:30