EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Catch Recognition in Automated American Football Training Using Machine Learning

Bernhard Hollaus iD, Bernhard Reiter, Jasper C Volmer

Sensors · 11.01.2023 · 23 (2) · 840

DOI: 10.3390/s23020840 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 11.01.2023. Verfasst von Bernhard Hollaus und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical, Health & Sports Engineering, MCI, 6020 Innsbruck, Austria. Hauptthemen laut MEDLINE: Football. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: department of Medical, Health and Sports Engineering at MCI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FootballHumansMachine LearningNeural Networks, ComputerRecords

Stichwörter der Autor:innen

American footballaction recognitioncatch trainingconvolutional neural networklong short term memorymachine learning

Autor:innen und Institutionen

  • Department of Medical, Health & Sports Engineering, MCI, 6020 Innsbruck, Austria.
  • Department of Mechatronics, MCI, 6020 Innsbruck, Austria.

ORCID-Profile: Bernhard Hollaus

Förderung

  • department of Medical, Health and Sports Engineering at MCI

Zitieren

APA

Hollaus, B., Reiter, B., & Volmer, J. C. (2023). Catch Recognition in Automated American Football Training Using Machine Learning. Sensors, 23(2), 840. https://doi.org/10.3390/s23020840

Vancouver

Hollaus B, Reiter B, Volmer JC. Catch Recognition in Automated American Football Training Using Machine Learning. Sensors. 2023;23(2):840. doi:10.3390/s23020840

BibTeX
@article{Hollaus2023,
  author = {Hollaus, Bernhard and Reiter, Bernhard and Volmer, Jasper C},
  title = {Catch Recognition in Automated American Football Training Using Machine Learning},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {2},
  pages = {840},
  doi = {10.3390/s23020840}
}
Kostenlos starten →