Cargando…

Catch Recognition in Automated American Football Training Using Machine Learning

In order to train receivers in American football in a targeted and individual manner, the strengths and weaknesses of the athletes must be evaluated precisely. As human resources are limited, it is beneficial to do it in an automated way. Automated passing machines are already given, therefore the m...

Descripción completa

Detalles Bibliográficos
Autores principales: Hollaus, Bernhard, Reiter, Bernhard, Volmer, Jasper C.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9864489/
https://www.ncbi.nlm.nih.gov/pubmed/36679637
http://dx.doi.org/10.3390/s23020840
_version_ 1784875597535641600
author Hollaus, Bernhard
Reiter, Bernhard
Volmer, Jasper C.
author_facet Hollaus, Bernhard
Reiter, Bernhard
Volmer, Jasper C.
author_sort Hollaus, Bernhard
collection PubMed
description In order to train receivers in American football in a targeted and individual manner, the strengths and weaknesses of the athletes must be evaluated precisely. As human resources are limited, it is beneficial to do it in an automated way. Automated passing machines are already given, therefore the motivation is to design a computer-based system that records and automatically evaluates the athlete’s catch attempts. The most fundamental evaluation would be whether the athlete has caught the pass successfully or not. An experiment was carried out to gain data about catch attempts that potentially contain information about the outcome of such. The experiment used a fully automated passing machine which can release passes on command. After a pass was released, an audio and a video sequence of the specific catch attempt was recorded. For this purpose, an audio-visual recording system was developed which was integrated into the passing machine. This system is used to create an audio and video dataset in the amount of 2276 recorded catch attempts. A Convolutional Neural Network (CNN) is used for feature extraction with downstream Long Short-Term Memory (LSTM) to classify the video data. Classification of the audio data is performed using a one-dimensional CNN. With the chosen neural network architecture, an accuracy of 92.19% was achieved in detecting whether a pass had been caught or not. The feasibility for automatic classification of catch attempts during automated catch training is confirmed with this result.
format Online
Article
Text
id pubmed-9864489
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-98644892023-01-22 Catch Recognition in Automated American Football Training Using Machine Learning Hollaus, Bernhard Reiter, Bernhard Volmer, Jasper C. Sensors (Basel) Article In order to train receivers in American football in a targeted and individual manner, the strengths and weaknesses of the athletes must be evaluated precisely. As human resources are limited, it is beneficial to do it in an automated way. Automated passing machines are already given, therefore the motivation is to design a computer-based system that records and automatically evaluates the athlete’s catch attempts. The most fundamental evaluation would be whether the athlete has caught the pass successfully or not. An experiment was carried out to gain data about catch attempts that potentially contain information about the outcome of such. The experiment used a fully automated passing machine which can release passes on command. After a pass was released, an audio and a video sequence of the specific catch attempt was recorded. For this purpose, an audio-visual recording system was developed which was integrated into the passing machine. This system is used to create an audio and video dataset in the amount of 2276 recorded catch attempts. A Convolutional Neural Network (CNN) is used for feature extraction with downstream Long Short-Term Memory (LSTM) to classify the video data. Classification of the audio data is performed using a one-dimensional CNN. With the chosen neural network architecture, an accuracy of 92.19% was achieved in detecting whether a pass had been caught or not. The feasibility for automatic classification of catch attempts during automated catch training is confirmed with this result. MDPI 2023-01-11 /pmc/articles/PMC9864489/ /pubmed/36679637 http://dx.doi.org/10.3390/s23020840 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Hollaus, Bernhard
Reiter, Bernhard
Volmer, Jasper C.
Catch Recognition in Automated American Football Training Using Machine Learning
title Catch Recognition in Automated American Football Training Using Machine Learning
title_full Catch Recognition in Automated American Football Training Using Machine Learning
title_fullStr Catch Recognition in Automated American Football Training Using Machine Learning
title_full_unstemmed Catch Recognition in Automated American Football Training Using Machine Learning
title_short Catch Recognition in Automated American Football Training Using Machine Learning
title_sort catch recognition in automated american football training using machine learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9864489/
https://www.ncbi.nlm.nih.gov/pubmed/36679637
http://dx.doi.org/10.3390/s23020840
work_keys_str_mv AT hollausbernhard catchrecognitioninautomatedamericanfootballtrainingusingmachinelearning
AT reiterbernhard catchrecognitioninautomatedamericanfootballtrainingusingmachinelearning
AT volmerjasperc catchrecognitioninautomatedamericanfootballtrainingusingmachinelearning