prikaz prve stranice dokumenta Procjena poze sportaša temeljeno na dubokom učenju
No public access
undergraduate thesis
Procjena poze sportaša temeljeno na dubokom učenju
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:625683
Čačinović, Marta
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Čačinović, M. (2023). Procjena poze sportaša temeljeno na dubokom učenju (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:625683

Čačinović, Marta. "Procjena poze sportaša temeljeno na dubokom učenju." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:625683

Čačinović, Marta. "Procjena poze sportaša temeljeno na dubokom učenju." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:625683

Čačinović, M. (2023). 'Procjena poze sportaša temeljeno na dubokom učenju', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 17 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:625683

Čačinović M. Procjena poze sportaša temeljeno na dubokom učenju [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 July 17] Available at: https://urn.nsk.hr/urn:nbn:hr:168:625683

M. Čačinović, "Procjena poze sportaša temeljeno na dubokom učenju", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:625683

Metadata
TitleProcjena poze sportaša temeljeno na dubokom učenju
Title (english)Athletes Pose Estimation Based on Deep Learning
AuthorMarta Čačinović
MentorVladimir Čeperić (mentor)
Committee memberVladimir Čeperić (predsjednik povjerenstva)
Committee memberVlatko Galić (član povjerenstva)
Committee memberAlma Traživuk (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad se bavi problemom procjene poze ljudskog tijela, konkretno sportaša, temeljenoj na dubokom učenju. Duboko učenje je jedna od podgrana strojnog učenja koje podučava računalne sustave da obrađuju podatke na način koji je sličan te inspiriran ljudskim mozgom. Konvolucijske neuronske mreže su odabrane kao prikladan model dubokog učenja. Objašnjeni su skupovi za učenje, provjeru i testiranje. Analiziran je utjecaj veličine mreže, različitih metoda regularizacije, aktivacijskih funkcija i tehnika učenja. Objašnjen je kod za dohvat podataka o kutu natkoljenice i potkoljenice koji nam govori radi li sportaš, u našem konkretnom slučaju trkač, dobre pokrete. Objašnjeno je zašto su ispravni pokreti u sportu bitni. Dobiveni rezultati su interpretirani te prikazani grafom.
Abstract (english)
This paper addresses the problem of human pose estimation, specifically for athletes, based on deep learning. Deep learning is a branch of machine learning that teaches computer systems to process data in a way that is similar to and inspired by the human brain. Convolutional neural networks have been chosen as a suitable deep learning model. Training, validation and testing sets have been explained. The impact of the size of the network, different regularization methods, activation functions, and learning techniques is analyzed. The code for retrieving the angle between the thigh and the shin, which indicates the correctness of movements for athletes, in our specific case, runners, is explained. It is explained why the correct movement in sports is important. The obtained results are interpreted and presented graphically.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:625683
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 on2023-10-11 08:37:27