Detekcija i praćenje kretanja igrača u videozapisima sportskih utakmica

master's thesis

• Title (english): Detection and Tracking of Players in Video Sequences of Sport Matches
• Author: Josip Salaheddin Paun Jarallah
• Mentor: Tomislav Hrkać (mentor)
• Committee member: Tomislav Hrkać (predsjednik povjerenstva)
• Committee member: Zoran Kalafatić (član povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Tema ovog diplomskog rada je detekcija i praćenje kretanja igrača u videozapisima sportskih utakmica. Najveći fokus ovog rada je na korištenje algoritama meanshift i camshift u praćenju kretnji, te na implementaciji istih koristeći OpenCV biblioteku i programski jezik Python. Testirana su oba algoritma na različitim videozapisima različitih sportova. Isto tako je testirano i više različitih metoda za detekciju igrača. U konačnoj implementaciji napravljeno je dvije inačice, od kojih jedna se koristi ručnom detekcijom i meanshift algoritmom za praćenje, dok se druga isto koristi ručnom detekcijom ljudi, ali camshift algoritmom za praćenje. Rezultati praćenja više igrača su spremljeni u xml datoteke.

Abstract (english)

The topic of this masters thesis is the detection and tracking of players in video sequences of sport matches. The main focus of this thesis is the use of the meanshift and camshift algorithms for tracking the movement of players and the implementation of those in Python while using the OpenCV library.
Both of the algorithms have been tested on different video sequences of different sport matches. Multiple methods for the detection of players have also been tested. In the final implementation there were two versions, one that consists of manual people detection and the meanshift algorithm for tracking, while the other also consists of manual people detection but uses the camshift algorithm for tracking. The results of tracking multiple players have been saved in XML files.

• Keywords: detekcija; histogram; praćenje kretanja; praćenje igrača; cam shift; mean shift; OpenCV
• Keywords (english): detection; histogram; motion tracking; player tracking; cam shift; mean shift; OpenCV
• Language: croatian
• URN:NBN: urn:nbn:hr:168:139442
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 23:39:23