This paper illustrates the development and the validation of a smart mirror for sport training. The application is based the skeletonization algorithm MediaPipe and runs on an embedded device Nvidia Jetson Nano equipped with two fisheye cameras. The software has been evaluated considering the exercise biceps curl. The elbow angle has been measured by both MediaPipe and the motion capture system BTS (ground truth), and the resulting values have been compared to determine angle uncertainty, residual errors, and intra-subject and inter-subject repeatability. The uncertainty of the joints’ estimation and the quality of the image captured by the cameras reflect on the final uncertainty of the indicator over time, highlighting the areas of improvements for further developments.

Deep Learning for Gesture Recognition in Gym Training performed by a vision-based augmented reality smart mirror

Lanza, Bernardo
Writing – Original Draft Preparation
;
Nuzzi, Cristina
Writing – Review & Editing
;
Pasinetti, Simone
Writing – Review & Editing
;
Lancini, Matteo
Project Administration
2022-01-01

Abstract

This paper illustrates the development and the validation of a smart mirror for sport training. The application is based the skeletonization algorithm MediaPipe and runs on an embedded device Nvidia Jetson Nano equipped with two fisheye cameras. The software has been evaluated considering the exercise biceps curl. The elbow angle has been measured by both MediaPipe and the motion capture system BTS (ground truth), and the resulting values have been compared to determine angle uncertainty, residual errors, and intra-subject and inter-subject repeatability. The uncertainty of the joints’ estimation and the quality of the image captured by the cameras reflect on the final uncertainty of the indicator over time, highlighting the areas of improvements for further developments.
File in questo prodotto:
File Dimensione Formato  
DEEP LEARNING FOR GESTURE RECOGNITION IN GYM TRAINING PERFORMED B.pdf

accesso aperto

Descrizione: Full_Paper
Tipologia: Documento in Post-print
Licenza: Creative commons
Dimensione 359.6 kB
Formato Adobe PDF
359.6 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11379/574987
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact