prikaz prve stranice dokumenta Određivanje korespondencija u slikama primjenom pažnje
No public access
undergraduate thesis
Određivanje korespondencija u slikama primjenom pažnje
2023. urn:nbn:hr:168:488208
Šarić, Dominik
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Šarić, D. (2023). Određivanje korespondencija u slikama primjenom pažnje (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:488208

Šarić, Dominik. "Određivanje korespondencija u slikama primjenom pažnje." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:488208

Šarić, Dominik. "Određivanje korespondencija u slikama primjenom pažnje." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:488208

Šarić, D. (2023). 'Određivanje korespondencija u slikama primjenom pažnje', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 02 May 2024, https://urn.nsk.hr/urn:nbn:hr:168:488208

Šarić D. Određivanje korespondencija u slikama primjenom pažnje [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 May 02] Available at: https://urn.nsk.hr/urn:nbn:hr:168:488208

D. Šarić, "Određivanje korespondencija u slikama primjenom pažnje", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:488208

Please login to the repository to save this object to your list.
Metadata
TitleOdređivanje korespondencija u slikama primjenom pažnje
Title (english)Recovering correspondences across images by means of attention
AuthorDominik Šarić
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarin Kačan (član povjerenstva)
Committee memberVjeko Kužina (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-06, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Pronalaženje korespondencija u parovima slika jedan je od temeljnih problema u računalnom vidu. Pronalaženje korespondencija može biti korisno u područjima poput kalibracije kamere, optičkog toka, vizualne lokalizacije i praćenja točaka. U ovom radu rješavamo problem korespondencije u parovima kalibriranih i rektificiranih slika koristeći konvolucijska ugrađivanja i modele koji koriste slojeve pažnje. Treniramo takav model na skupu podataka KITTI 2015, na kojem provodimo eksperimente i primjene.
Abstract (english)
Finding correspondences in pairs of images is one of the fundamental problems in computer vision. Discovering correspondences can be useful in areas such as camera calibration, optical flow, visual localization, and point tracking. In this paper, we tackle the correspondence problem in pairs of calibrated and rectified images using convolutional embeddings and models that employ attention layers. We train such a model on a publicly available dataset KITTI 2015, on which we conduct experiments and applications.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:488208
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-07-13 10:34:59