Detekcija igrača u snimkama nogometnih utakmica temeljena na dubokom učenju

master's thesis

• Title (english): Player Detection in Football Game Video Based on Deep Learning
• Author: Davor Šafranko
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Tomislav Hrkać (član povjerenstva)
• Committee member: Marin Šilić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-17, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad bavi se problemom detekcije igrača u snimkama nogometnih utakmica koristeći duboko učenje. Dan je kratak uvod u područje računalnog vida te probleme koje to područje rješava. Opisane se konvolucijske neuronske mreže te metode slaganja dubokih modela i načini njihova učenja. Zatim su opisane neke metode dubokog učenja za detekciju i semantičku segmentaciju. Također je opisan model za semantičku segmentaciju terena i igrača implementiran u ovom radu. Na kraju su prikazani i komentirani rezultati implementiranog sustava za semantičku segmentaciju.

Abstract (english)

This paper deals with the problem of detecting players in footage of football matches using deep learning. A brief introduction to the field of computer vision and its tasks is provided. Convolutional neural networks and methods for building and learning deep networks are described. Some methods for object detection and semantic segmentation using deep learning are presented. Semantic segmentation model and its implementation are described. At the end the results of the implemented system are shown and explained.

• Keywords: Nogomet; semantička segmentacija; duboko učenje; konvolucijska neuronska mreža; detekcija; računalni vid; TensorFlow
• Keywords (english): Football; semantic segmentation; deep learning; convolutional neural network; detection; computer vision; TensorFlow
• Language: croatian
• URN:NBN: urn:nbn:hr:168:974048
• 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: 2019-03-14 01:03:37