A tennis training application using 3D gesture recognition
García Bauza, Cristián
A tennis training application using 3D gesture recognition - 1 archivo (822,5 KB)
Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
This paper presents a sport training system which recognizes user movements from data of the Wiimote device with accelerometer technology. Recognizing a new gesture involves the normalization of the Wiimote data and searching in a gesture templates database. The Dynamic Time Warping (DTW) comparison algorithm is used as a correlation function to compare the new gesture with every template. Based on prior training, the system can successfully recognize different sport shots. Particularly the system is instantiated for tennis training. The user visualizes the trajectory of the ball in a three-dimensional environment and he can interact with virtual objects that follow Newton dynamics.
DIF-M6785
VIDEOJUEGOS
ENTRENAMIENTO DEPORTIVO
GRÁFICOS
A tennis training application using 3D gesture recognition - 1 archivo (822,5 KB)
Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
This paper presents a sport training system which recognizes user movements from data of the Wiimote device with accelerometer technology. Recognizing a new gesture involves the normalization of the Wiimote data and searching in a gesture templates database. The Dynamic Time Warping (DTW) comparison algorithm is used as a correlation function to compare the new gesture with every template. Based on prior training, the system can successfully recognize different sport shots. Particularly the system is instantiated for tennis training. The user visualizes the trajectory of the ball in a three-dimensional environment and he can interact with virtual objects that follow Newton dynamics.
DIF-M6785
VIDEOJUEGOS
ENTRENAMIENTO DEPORTIVO
GRÁFICOS