prikaz prve stranice dokumenta Nenadzirano učenje modela za monokularnu procjenu dubine
No public access
master's thesis
Nenadzirano učenje modela za monokularnu procjenu dubine
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:957646
Bilić, Ivan
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Bilić, I. (2021). Nenadzirano učenje modela za monokularnu procjenu dubine (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:957646

Bilić, Ivan. "Nenadzirano učenje modela za monokularnu procjenu dubine." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:957646

Bilić, Ivan. "Nenadzirano učenje modela za monokularnu procjenu dubine." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:957646

Bilić, I. (2021). 'Nenadzirano učenje modela za monokularnu procjenu dubine', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 18 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:957646

Bilić I. Nenadzirano učenje modela za monokularnu procjenu dubine [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 December 18] Available at: https://urn.nsk.hr/urn:nbn:hr:168:957646

I. Bilić, "Nenadzirano učenje modela za monokularnu procjenu dubine", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:957646

Metadata
TitleNenadzirano učenje modela za monokularnu procjenu dubine
Title (english)Unsupervised learning of models for monocular depth estimation
AuthorIvan Bilić
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarko Čupić (član povjerenstva)
Committee memberIvan Petrović (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-07-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Monokularna procjena dubine loše je postavljen problem kojeg karakterizira nedostatak geometrijskih ograničenja, a primjena dubokog učenja pokazuje se plodonosnom u računalnom vidu. Pristup zadatku podrazumijeva nenadzirano učenje dubokih konvolucijskih neuronskih mreža za procjenu dubine i relativne poze kamere, temeljenih na široko rasprostranjenoj arhitekturi U-Net. Pojedine induktivne pristranosti te korisna geometrijska svojstva - poput rijetke povezanosti i ekvivarijantnosti s obzirom na pomak, razlog su zbog kojeg spomenute arhitekture predstavljaju prikladan alat za rješavanje navedenog zadatka. Matematički okvir za nenadzirano učenje monokularne procjene dubine proizlazi iz modela kamere i geometrije nastanka slike, a svodi se na zadatak rekonstrukcije. Kod monokularnog pristupa, posebno se ističe problem skale te potreba za modelom za procjenu relativne poze kamere - dva povezana problema kojih nema kod stereo pristupa. Kvalitativni rezultati pokazuju pojedine učinke učenja i ugađanja modela na skupu KITTI te na internom skupu BIH. Arhitekturalne značajke poput procjene aleatorne nesigurnosti, rekonstrukcije značajki i mehanizma pozornosti, pokazuju se kao kompetitivne. Eksperimenti također pokazuju da se performanse monodepth2 modela na KITTI Eigen testnom skupu mogu unaprijediti pažljivijim odabirom vrijednosti pojedinih hiperparametara te upotrebom transponirane konvolucije za naduzorkovanje. Svi eksperimenti su temeljeni na monodepth2 modelu.
Abstract (english)
Monocular depth estimation is an ill-posed problem that suffers from lack of geometric constraints, whilst deep learning has already proven itself for a variety of computer vision tasks. The approach consists of training deep convolutional neural networks deployed as popular and widely used U-Net architecture. These tools are known for possessing desirable inductive biases (e.g. sparse connectivity) and geometric properties (e.g. translational equivariance). Unsupervised learning for monocular depth estimation is enabled by a mathematical framework that arises from single view geometry and the pinhole camera model; the neural networks are trained to perform warping-based view synthesis. The "scale problem" and the need for relative camera pose estimation model are the key differences between monocular and stereo approach. Qualitative results show the effects of training and fine-tuning on KITTI and internal BIH datasets. Architectural features such as aleatoric uncertainty estimation, multi-scale feature reconstruction and attention mechanism are also competitive. Experiments also show that monodepth2 performance on KITTI Eigen test set can be improved by choosing different hyperparameter values and using transposed convolution for upsampling. All experiments are based on monodepth2 model.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:957646
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 11:49:23