Thesis Details
Rozpoznávání událostí ve fotbalu z prostoročasových dat objektů ve hře
This diploma thesis deals with automatic soccer event detection. Its goal is to introduce reader to this issue, discuss possible ways of solution of this task and then implement event detection. This work aims at event recognition using spatio-temporal data of gaming objects. Introduced way of dealing with event detection lies in its converting to sequence labeling task. Then such task is solved using LSTM recurrent neural networks. Lastly, result of sequence labeling is interpreted as detected events. Library for event detection has been created as the output of this work. This library allow user to experiment with different variants how to formulate event detection as sequence labeling task.
event detection, soccer, spatio-temporal data, machine learning, sequence labeling, artifical neural network
Bidlo Michal, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Grézl František, Ing., Ph.D. (DCGM FIT BUT), člen
Matoušek Radomil, doc. Ing., Ph.D. (IACS FME BUT), člen
Meduna Alexander, prof. RNDr., CSc. (DIFS FIT BUT), člen
Peringer Petr, Dr. Ing. (DITS FIT BUT), člen
@mastersthesis{FITMT20871,
author = "Tom\'{a}\v{s} \v{C}\'{i}\v{z}ek",
type = "Master's thesis",
title = "Rozpozn\'{a}v\'{a}n\'{i} ud\'{a}lost\'{i} ve fotbalu z prostoro\v{c}asov\'{y}ch dat objekt\r{u} ve h\v{r}e",
school = "Brno University of Technology, Faculty of Information Technology",
year = 2018,
location = "Brno, CZ",
language = "czech",
url = "https://www.fit.vut.cz/study/thesis/20871/"
}