Hockey activity recognition using pre-trained deep learning model

Activity recognition in sports is often complex task resulting from the rapid dynamic interaction within players. In this paper, pre-trained VGG-16, deep learning based hockey activity recognition model has been proposed. Own hockey dataset consisting of four main activity includes free hit, goal, p...

Full description

Bibliographic Details
Main Authors: Keerthana Rangasamy, Muhammad Amir As’ari, Nur Azmina Rahmad, Nurul Fathiah Ghazali
Format: Article
Language:English
Published: Elsevier 2020-09-01
Series:ICT Express
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405959520300114
_version_ 1818247865688915968
author Keerthana Rangasamy
Muhammad Amir As’ari
Nur Azmina Rahmad
Nurul Fathiah Ghazali
author_facet Keerthana Rangasamy
Muhammad Amir As’ari
Nur Azmina Rahmad
Nurul Fathiah Ghazali
author_sort Keerthana Rangasamy
collection DOAJ
description Activity recognition in sports is often complex task resulting from the rapid dynamic interaction within players. In this paper, pre-trained VGG-16, deep learning based hockey activity recognition model has been proposed. Own hockey dataset consisting of four main activity includes free hit, goal, penalty corner and long corner was constructed as there are no existing field hockey datasets available. Experimental results indicate that the pre-trained deep learning model generates comparative results on this challenging dataset by tweaking the hyperparameters of this pre-trained model.
first_indexed 2024-12-12T15:11:30Z
format Article
id doaj.art-7122846b2c0448f1b4de49da5a0d979c
institution Directory Open Access Journal
issn 2405-9595
language English
last_indexed 2024-12-12T15:11:30Z
publishDate 2020-09-01
publisher Elsevier
record_format Article
series ICT Express
spelling doaj.art-7122846b2c0448f1b4de49da5a0d979c2022-12-22T00:20:37ZengElsevierICT Express2405-95952020-09-0163170174Hockey activity recognition using pre-trained deep learning modelKeerthana Rangasamy0Muhammad Amir As’ari1Nur Azmina Rahmad2Nurul Fathiah Ghazali3School of Biomedical Engineering and Health Sciences, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia; Corresponding author.School of Biomedical Engineering and Health Sciences, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia; Sport Innovation and Technology Center (SITC), Institute of Human Centered Engineering (IHCE), Universiti Teknologi Malaysia, Johor Bahru, MalaysiaSchool of Biomedical Engineering and Health Sciences, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru, MalaysiaSchool of Biomedical Engineering and Health Sciences, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru, MalaysiaActivity recognition in sports is often complex task resulting from the rapid dynamic interaction within players. In this paper, pre-trained VGG-16, deep learning based hockey activity recognition model has been proposed. Own hockey dataset consisting of four main activity includes free hit, goal, penalty corner and long corner was constructed as there are no existing field hockey datasets available. Experimental results indicate that the pre-trained deep learning model generates comparative results on this challenging dataset by tweaking the hyperparameters of this pre-trained model.http://www.sciencedirect.com/science/article/pii/S2405959520300114Sport video analysisDeep learningActivity recognition
spellingShingle Keerthana Rangasamy
Muhammad Amir As’ari
Nur Azmina Rahmad
Nurul Fathiah Ghazali
Hockey activity recognition using pre-trained deep learning model
ICT Express
Sport video analysis
Deep learning
Activity recognition
title Hockey activity recognition using pre-trained deep learning model
title_full Hockey activity recognition using pre-trained deep learning model
title_fullStr Hockey activity recognition using pre-trained deep learning model
title_full_unstemmed Hockey activity recognition using pre-trained deep learning model
title_short Hockey activity recognition using pre-trained deep learning model
title_sort hockey activity recognition using pre trained deep learning model
topic Sport video analysis
Deep learning
Activity recognition
url http://www.sciencedirect.com/science/article/pii/S2405959520300114
work_keys_str_mv AT keerthanarangasamy hockeyactivityrecognitionusingpretraineddeeplearningmodel
AT muhammadamirasari hockeyactivityrecognitionusingpretraineddeeplearningmodel
AT nurazminarahmad hockeyactivityrecognitionusingpretraineddeeplearningmodel
AT nurulfathiahghazali hockeyactivityrecognitionusingpretraineddeeplearningmodel