20.500.12556/DKUM-97301 Video Annotation With Metadata: A Case Study of Soccer Game Video Annotation With Players Video Annotation With Metadata: A Case Study of Soccer Game Video Annotation With Players Označevanje videa z metapodatki analiza primera označevanja videa posnetka nogometne tekme s podatki o igralcih In recent years, the use of convolutional neural networks for video processing has become very attractive. The reason lies in the computational power for data processing which is available today. There are many well-defined research areas where neural networks have brought higher reliability than other conventional approaches; for example, traffic sign recognition and isolated number recognition. In this paper, we will describe the architecture and the implementation of the process of soccer game annotation. The game is annotated with data about players. The technology of convolutional neural networks is used for number recognition. The process runs in real-time on a streaming video. Content enriched with metadata is given to the user in parallel with the real-time video. In the paper, we will describe in some detail the following modules: Image binarization, shot localization, the selection and recognition of numbers on players` jerseys. V zadnjih letih je uporaba konvolucijskih nevronskih mrež pri procesiranju video vsebin doživela velik razcvet. Razlog je predvsem v povečani računski moči, ki je danes na voljo za procesiranje podatkov. Na posameznih dobro definiranih področjih, kot so na primer razpoznava obrazov, razpoznava prometnih znakov in izoliranih števil, zagotavlja tehnologija nevronskih mrež visoko zanesljivost. V prispevku bomo opisali arhitekturo in implementacijo procesa označevanja nogometne tekme s podatki o imenih igralcev z uporabo tehnologije nevronskih mrež. Proces se izvaja realno-časovno nad videom razpršene oddaje. Obogatena vsebina je ponujena uporabniku na ogled sočasno z video posnetkom. V prispevku bomo opisali celoten proces, ki je sestavljen iz naslednjih korakov: binarizacije slike, lokalizacije dresov nogometašev, izločanja ter razpoznavanja števil, zapisanih na dresih. Podali bomo tudi rezultate evalvacije sistema. video annotation convolutional neural networks football označevanje videa konvolucijske nevronske mreže nogomet true false true Univerza v Mariboru, Univerzitetna založba Angleški jezik Slovenski jezik Znanstveno delo 2026-02-27 08:29:18 2026-02-27 08:29:18 2026-04-09 07:20:39 0000-00-00 00:00:00 2019 0 Maribor 0 8 št.1/2 Letn.9 2019 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 2019-01-01 621.39 20393475 10.18690/analipazu.9.1-2.30-37.2019 2820-364X Video_Annotation_With-Zimsek-2019.pdf Video_Annotation_With-Zimsek-2019.pdf 1 33B6D2FA465E1A944F79C018E77B9549 853de12e54ab64599dc839986cb10364bd131e7784862bff4f3d4f914a27e1cd 6dbfdb63-13ae-11f1-bb89-00155d580e1a https://dk.um.si/Dokument.php?lang=slv&id=203974 https://journals.um.si/index.php/anali-pazu/article/view/2003 0 5549b26c-13ae-11f1-bb89-00155d580e1a https://dk.um.si/Dokument.php?lang=slv&id=203972 Univerzitetna založba Univerze v Mariboru Anali PAZU 0 0 0