prikaz prve stranice dokumenta Detekcija igrača u video zapisu nogometne utakmice primjenom YOLO detektora
Access restricted to students and staff of home institution
undergraduate thesis
Detekcija igrača u video zapisu nogometne utakmice primjenom YOLO detektora
2021. urn:nbn:hr:179:998088
Kuten, Ana
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Kuten, A. (2021). Detekcija igrača u video zapisu nogometne utakmice primjenom YOLO detektora (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:998088

Kuten, Ana. "Detekcija igrača u video zapisu nogometne utakmice primjenom YOLO detektora." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:998088

Kuten, Ana. "Detekcija igrača u video zapisu nogometne utakmice primjenom YOLO detektora." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:998088

Kuten, A. (2021). 'Detekcija igrača u video zapisu nogometne utakmice primjenom YOLO detektora', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 16 April 2024, https://urn.nsk.hr/urn:nbn:hr:179:998088

Kuten A. Detekcija igrača u video zapisu nogometne utakmice primjenom YOLO detektora [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 April 16] Available at: https://urn.nsk.hr/urn:nbn:hr:179:998088

A. Kuten, "Detekcija igrača u video zapisu nogometne utakmice primjenom YOLO detektora", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:998088

Please login to the repository to save this object to your list.
Metadata
TitleDetekcija igrača u video zapisu nogometne utakmice primjenom YOLO detektora
Title (english)Players detection in football match video using YOLO detector
AuthorAna Kuten
MentorMatko Šarić (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-09-21, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
Umjetna inteligencija i strojno učenje koriste se u različitim područjima života. Strojno učenje koristi neuralne mreže koje se sastoje od umjetnih neurona kreiranih prema pravim biološkim neuronima. Postoji više vrsta neuralnih mreža a jedna od najviše korištenih je konvolucijska neuralna mreža. Pomoću nje je moguće istrenirati mrežu da prepoznaje i klasificira različite objekte na slikama i videozapisima. Ova mreža sastoji se od ulaza, konvolucijskog sloja, sloja sažimanja, potpuno povezanog sloja te izlaza. Konvolucijski sloj je najvažniji za rad konvolucijske neuralne mreže. Konvolucijski sloj primjenjuje operaciju konvolucije na ulaz. To možemo promatrati kao jednostavnu primjenu filtra na ulaz mreže. Za detekciju igrača u videozapisu nogometne utakmice korištena je YOLO arhitektura, programski jezik Python te biblioteka Keras unutar programskog jezika Python. YOLO arhitektura je jedan od najmoćnijih i najčešće korištenih algoritama za detekciju objekata u stvarnom vremenu. Python je višenamjenski programski jezik. Moguće ga je primijeniti gotovo svugdje gdje se koriste podaci i matematičko izračunavanje. Keras je najčešće korištena biblioteka za duboko učenje napisana u Pythonu. Podržava višestruke pozadinske računalne sustave za neuralne mreže. Izrađena je na temelju platforme za strojno učenje TensorFlow. Nakon pokretanja i uspješnog izvršavanja koda koji detektira igrače u videozapisu, kao rezultat smo dobili slike na kojima je svaki igrač označen graničnim okvirom što znači da je mreža uspješno detektirala igrače.
Abstract (english)
Artificial intelligence and machine learning are used in different areas of life. Machine learning uses neural networks consisting of artificial neurons made according to real biological neurons. There are several types of neural networks and one of the most used is the convolutional neural network. It allows you to train the network to recognize and classify different objects in images and videos. This network consists of an input, a convolutional layer, a pooling layer, a fully connected layer, and an output. The convolutional layer is most important for the operation of the convolutional neural network. The convolution layer applies a convolution operation to the input. We can observe this as a simple application of a filter to the network input. The YOLO architecture, the Python programming language and the Keras library within the Python programming language were used to detect players in a football match video. The YOLO architecture is one of the most powerful and commonly used algorithms for real-time object detection. Python is a multi-purpose programming language. It can be applied where data and mathematical calculation are used. Keras is the most commonly used deep learning library written in Python. It supports multiple background computer systems for neural networks. It is based on the TensorFlow machine learning platform. After running and successfully executing the code which detects players in video, as a result we got images in which each player is marked with a border frame meaning that the network has successfully detected the players.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:998088
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-12-07 10:58:22