prikaz prve stranice dokumenta Umjetna inteligencija u procjeni položaja tijela
  Download
PDF 1.46 MB
undergraduate thesis
Umjetna inteligencija u procjeni položaja tijela
2019. urn:nbn:hr:166:204281
Novaković, Lora
University of Split
Faculty of Science
Department of Informatics

Cite this document

Novaković, L. (2019). Umjetna inteligencija u procjeni položaja tijela (Undergraduate thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:204281

Novaković, Lora. "Umjetna inteligencija u procjeni položaja tijela." Undergraduate thesis, University of Split, Faculty of Science, 2019. https://urn.nsk.hr/urn:nbn:hr:166:204281

Novaković, Lora. "Umjetna inteligencija u procjeni položaja tijela." Undergraduate thesis, University of Split, Faculty of Science, 2019. https://urn.nsk.hr/urn:nbn:hr:166:204281

Novaković, L. (2019). 'Umjetna inteligencija u procjeni položaja tijela', Undergraduate thesis, University of Split, Faculty of Science, accessed 13 November 2024, https://urn.nsk.hr/urn:nbn:hr:166:204281

Novaković L. Umjetna inteligencija u procjeni položaja tijela [Undergraduate thesis]. Split: University of Split, Faculty of Science; 2019 [cited 2024 November 13] Available at: https://urn.nsk.hr/urn:nbn:hr:166:204281

L. Novaković, "Umjetna inteligencija u procjeni položaja tijela", Undergraduate thesis, University of Split, Faculty of Science, Split, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:166:204281

Please login to the repository to save this object to your list.
Metadata
TitleUmjetna inteligencija u procjeni položaja tijela
Title (english)Artificial intelligence in pose estimation
AuthorLora Novaković
MentorSaša Mladenović (mentor)
MentorGoran Zaharija (pomoć pri izradi, neposredni voditelj)
Committee memberSaša Mladenović (predsjednik povjerenstva)
Committee memberGoran Zaharija (član povjerenstva)
Committee memberDivna Krpan (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Informatics)
Split
Defense date and country2019-07-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu se prikazuje način na koji računalo može detektirati naše pokrete putem web kamere. Spominje se koja gotova biblioteka je najjednostavnija za korištenje - PoseNet. Pobliže se objašnjava rad neuronskih mreža, s naglaskom na konvolucijske neuronske mreže, koje su se pokazale jako pouzdane kad je riječ o obradi slika. S obzirom da ne treniramo sami mrežu, nije objašnjen detaljno način učenja mreže.
Abstract (english)
This paper shows how the computer can detect our movements via web camera. It mentions which library is the easiest to use. It is closely explained how neural networks work, with an emphasis on convolutional neural networks, which has proved to be very reliable when dealing with image processing. Since we are not training the network itself, we have not explained the detailed way of learning the network.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:204281
Study programmeTitle: Computer Science
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) icon
Created on2020-02-03 16:23:51