Title
A tennis training application using 3d gesture recognition
Abstract
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.
Year
DOI
Venue
2012
10.1007/978-3-642-31567-1_24
AMDO
Keywords
Field
DocType
dynamic time warping,tennis training,gesture templates database,tennis training application,wiimote data,wiimote device,different sport shot,sport training system,prior training,gesture recognition,user movement,new gesture
Computer vision,Normalization (statistics),Dynamic time warping,Accelerometer,Gesture,Training system,Computer science,Gesture recognition,Artificial intelligence,Computer graphics,Trajectory
Conference
Volume
ISSN
Citations 
7378
0302-9743
0
PageRank 
References 
Authors
0.34
8
7