Analiza kretanja igrača u ravnini terena na temelju videozapisa sportske utakmice

undergraduate thesis

• Title (english): Analysis of Player Motion in Ground Plane Based on Sport Match Video Sequence
• Author: Ante Bundović
• Mentor: Tomislav Hrkać (mentor)
• Committee member: Tomislav Hrkać (predsjednik povjerenstva)
• Committee member: Karla Brkić (član povjerenstva)
• Committee member: Darijan Marčetić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu opisana je ideja i postupak detekcije nogometnih igrača u videozapisu nogometne utakmice te analiza njihovog kretanja na slici tlocrta igrališta. Objašnjena je primjena i potreba za programom takve vrste.

Opisan je postupak metodom "oduzimanje pozadine" te je za usporedbu uzeta datoteka s već pripremljenim podacima o detektiranim igračima. Cilj je bio napraviti statistiku kretanja igrača, odnosno iscrtati na igralištu gdje su se igrači najviše kretali, a gdje najmanje.

Izrada aplikacije potpomognuta je bibliotekom OpenCV, objašnjene se korištene funkcije te razlog njihovog korištenja.

Na kraju su prezentirani rezultati uspješnosti aplikacije u usporedbi s već poznatim podacima. Dane su smjernice za moguće daljnje poboljšanje algoritma i aplikacije.

Abstract (english)

This paper describes an idea and process of development of detection of football players based on video match sequence and analysis of their movement in ground plane based picture of football pitch. The use and the need off such application is described.

Background subtraction method is described, and for comparation it's used file with already computed data of detected players. The goal was to make a simple statistics about players movement, respectivly, to draw in a football pitch picture the area where the players moved the most, and where the least.

The development of the application was based on OpenCV library, the methods used were described, and so was the reason of their use.

In the end, the results were presented in comparation with already computed data.
Finally, guidance was given for possible improvement of the algorithm and the application.

• Keywords: analiza kretanja igrača; računalni vid; OpenCV; nogomet
• Keywords (english): Analysis of player motion; OpenCV; computer vision; football
• Language: croatian
• URN:NBN: urn:nbn:hr:168:054638
• 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: 2019-03-13 19:28:02