prikaz prve stranice dokumenta Procjena dubine prostora iz 2D slika korištenjem konvolucijske neuronske mreže
  Download
PDF 1.78 MB
undergraduate thesis
Procjena dubine prostora iz 2D slika korištenjem konvolucijske neuronske mreže
2023. urn:nbn:hr:235:998547
Zeba, Ilija
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Cite this document

Zeba, I. (2023). Procjena dubine prostora iz 2D slika korištenjem konvolucijske neuronske mreže (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:998547

Zeba, Ilija. "Procjena dubine prostora iz 2D slika korištenjem konvolucijske neuronske mreže." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2023. https://urn.nsk.hr/urn:nbn:hr:235:998547

Zeba, Ilija. "Procjena dubine prostora iz 2D slika korištenjem konvolucijske neuronske mreže." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2023. https://urn.nsk.hr/urn:nbn:hr:235:998547

Zeba, I. (2023). 'Procjena dubine prostora iz 2D slika korištenjem konvolucijske neuronske mreže', Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 23 February 2025, https://urn.nsk.hr/urn:nbn:hr:235:998547

Zeba I. Procjena dubine prostora iz 2D slika korištenjem konvolucijske neuronske mreže [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2023 [cited 2025 February 23] Available at: https://urn.nsk.hr/urn:nbn:hr:235:998547

I. Zeba, "Procjena dubine prostora iz 2D slika korištenjem konvolucijske neuronske mreže", Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:235:998547

Please login to the repository to save this object to your list.
Metadata
TitleProcjena dubine prostora iz 2D slika korištenjem konvolucijske neuronske mreže
Title (english)Estimation of space depth from 2D images using a convolutional neural network
AuthorIlija Zeba
MentorTomislav Stipančić (mentor)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2023-03-02, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
U radu se koristi konvolucijska neuronska mreža kako bi se procijenila dubina prostora iz 2D slike. Mreža prima 2D sliku kao ulaz i izlazi s odgovarajućom kartom dubine koja predstavlja procijenjenu dubinu za svaki piksel u slici. Da bi se mreža naučila predviđati dubinu, koristi se velika skupina podataka 2D slika i njihova odgovarajuća istinita karta dubine. Mreža uči predviđati dubinu smanjujući razliku između procijenjenih karata dubine i istinitih karata dubine.
Abstract (english)
In this paper convolutional neural network is used to estimate the depth of space from a 2D image as input and outputs a corresponding depth map that represents the estimated depth from each pixel in the image. To learn the network to predict depth, a large dataset od 2D images and their corresponding true depth map is used. The network can predict depth by reducing the difference between the estimated depth maps and the true depth maps.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:235:998547
Study programmeTitle: Mechanical Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-02-28 17:50:22
accessibility

closeAccessibilityrefresh

If you wish to permanently save changes, click on Save, if not - your settings will be reset when you restart the browser.