With the development of wearable technology and inertial sensor technology, the application of wearable sensors in the field of sports is becoming more extensive. The notion of Body Sensor Network (BSN) brings unique human-computer interaction mode and gives users a brand new experience. In terms of smart sports, BSN can be applied to table tennis training by detecting individual stroke motion and recognizing different technical movements, which provide a training evaluation for the players to improve their sport skills. A portable six-degree-of-freedom inertial sensor system was adopted to collect data in this research. After data pre-processing, triaxial angular velocity and triaxial acceleration data were used for table tennis stroke motion recognition. The classification and recognition of stroke action were achieved based on Support Vector Machine (SVM) algorithm after Principal Component Analysis (PCA) dimension reduction, and the recognition rate of five typical strokes can reach up to $$96%$$ using the trained classification model. It can be assumed that BSN has practical significance and broad application prospects.

Motion Recognition for Smart Sports Based on Wearable Inertial Sensors

Gravina R.
2019-01-01

Abstract

With the development of wearable technology and inertial sensor technology, the application of wearable sensors in the field of sports is becoming more extensive. The notion of Body Sensor Network (BSN) brings unique human-computer interaction mode and gives users a brand new experience. In terms of smart sports, BSN can be applied to table tennis training by detecting individual stroke motion and recognizing different technical movements, which provide a training evaluation for the players to improve their sport skills. A portable six-degree-of-freedom inertial sensor system was adopted to collect data in this research. After data pre-processing, triaxial angular velocity and triaxial acceleration data were used for table tennis stroke motion recognition. The classification and recognition of stroke action were achieved based on Support Vector Machine (SVM) algorithm after Principal Component Analysis (PCA) dimension reduction, and the recognition rate of five typical strokes can reach up to $$96%$$ using the trained classification model. It can be assumed that BSN has practical significance and broad application prospects.
2019
978-3-030-34832-8
978-3-030-34833-5
Body sensor network; Information fusion; Micro-electro-mechanical sensor; Motion recognition; Wearable computing
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/20.500.11770/299206
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? ND
social impact