Sustav za detekciju i praćenje igrača u sportu

master's thesis

• Title (english): System for detection and tracking of players in sports
• Author: Krunoslav Malenica
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Ante Đerek (član povjerenstva)
• Committee member: Tomislav Hrkać (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U radu je opisana osnovna problematika u izradi sustava za praćenje sportaša u sportu.
Opisano je nekoliko načina segmentacije slike koji se koriste u ovakvim sustavima kao što
je oduzimanje pozadine, projekcija histograma, ekstrakcija pomoću vršne vrijednosti, stroj
s potpornim vektorima, Cannyjev detektor ruba, Hughova linijska transformacija, a za
praćenje igrača je opisan Kalmanov i čestični filtar. U radu je opisano nekoliko sličnih
istraživanja, te je uz pomoć biblioteke OpenCV implementiran jednostavan sustav praćenja
nogometaša na video snimci. Opisan je način korištenja i način rada programskog rješenja,
te je provedeno mjerenje uspješnosti, a time i otkrivene slabosti sustava.

Abstract (english)

This master thesis offers a description of basic problems regarding building systems for
tracking sport players. Descriptions of image segmentation methods such as background
subtraction, histogram backprojection, peak value extraction, Canny edge detector, Hugh
line transformation and support vector machine are given. Popular methods for tracking
players such as Kalman and particle filter are described in the thesis. A simple football
players tracking system has been implemented by using OpenCV library. Implementation
details are given as well as the instructions for using the system. The implementation has
been tested on a video and results have been commented.

• Keywords: nogomet; praćenje; čestični filtar; Kalmanov filtar; projekcija histograma; stroj s potpornim vektorima
• Keywords (english): football; tracking; particle filter; Kalman filter; histogram backprojection; support vector machine
• Language: croatian
• URN:NBN: urn:nbn:hr:168:387284
• 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: 2018-02-06 10:16:20