Određivanje kretanja igrača u koordinatnom sustavu igrališta na temelju videozapisa sportskih utakmica

undergraduate thesis

• Title (english): Determining Player Movement in Playground Coordinate System Based on Video Sequences of Sport Matches
• Author: Daniel Bratulić
• Mentor: Tomislav Hrkać (mentor)
• Committee member: Tomislav Hrkać (predsjednik povjerenstva)
• Committee member: Danko Ivošević (član povjerenstva)
• Committee member: Karla Brkić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Umjetna inteligencija svakim danom ima sve više utjecaja na ljudski život. Tako je počela utjecati i u svijetu sporta gdje se područje računalnog vida sve više primjenjuje. U ovom radu sam korištenjem algoritama računalnog vida preslikao pozicije igrača sa snimke nogometnih utakmica na tlocrt nogometnog terena. Algoritmom oduzimanja pozadine dobiveni su objekti koji se nalaze na prednjoj strani slike. U ovisnosti o karakterističnim točkama terena promatraju se samo objekti unutar granica nogometnog terena, te su njihovi položaji preslikani na tlocrt nogometnog terena koristeći perspektivnu transformaciju. Morfološkim transformacijama je poboljšano očitavanje pokretnih objekata.

Abstract (english)

Artificial intelligence is having more and more influence in people's lives every day. It started to influence world of sports as well, where computer vision is having increased influence. In this work I used computer vision algorithms to map players' movements from videos of soccer matches to layout of soccer pitch. Using background subtraction algorithm foreground objects on each frame are obtained. Depending on characteristic points of soccer pitch only objects inside the boundaries of pitch are observed and their positions are mapped to layout of soccer field. Detecting moving objects is improved using morphological transformations.

• Keywords: Računalni vid; oduzimanje pozadine; morfološke transformacije; perspektivna transformacija; umjetna inteligencija; Python
• Keywords (english): Computer vision; background subtraction; morphological transformations; perspective transformation; artificial intelligence; Python
• Language: croatian
• URN:NBN: urn:nbn:hr:168:294719
• Study programme: Title: 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 08:01:20