A Real-time Personalized Gesture Interaction System Using Wii Remote and Kinect for Tiled-Display Environment

Gesture interaction is more convenient than traditional input methods in tiled-display environments. As the advance of somatosensory technologies, more and more somatosensory devices such as Wii Remote and Kinect that can be used in gesture interaction are commercially available. We present a real-time personalized gesture interaction system targeting for two-handed gestures for tiled-display environment in this paper. By applying the dynamic time warping (DTW) algorithm, the system does not require a special training stage and is easy to use. Experiment shows that the combination of acceleration data from Wii Remote and skeleton point data from Kinect leads to higher recognition accuracy with lower recognition error rate, and the system can also recognize an ongoing gesture before it ends while the recognition accuracy is kept high enough. Our usage of this system in a real tiled-display environment shows that the system is practical.

[1]  Elena Mugellini,et al.  Context-Aware 3D Gesture Interaction Based on Multiple Kinects , 2011 .

[2]  S. Mitra,et al.  Gesture Recognition: A Survey , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[3]  Zhen Wang,et al.  uWave: Accelerometer-based Personalized Gesture Recognition and Its Applications , 2009, PerCom.

[4]  Andrew E. Johnson,et al.  High-Performance Dynamic Graphics Streaming for Scalable Adaptive Graphics Environment , 2006, ACM/IEEE SC 2006 Conference (SC'06).

[5]  Wenjun Wu,et al.  Magic Input: A Multi-user Interaction System for SAGE Based Large Tiled-display Environment , 2012, 2012 IEEE International Conference on Multimedia and Expo Workshops.

[6]  Aude Billard,et al.  Recognition and reproduction of gestures using a probabilistic framework combining PCA, ICA and HMM , 2005, ICML.

[7]  Janusz Konrad,et al.  A gesture-driven computer interface using Kinect , 2012, 2012 IEEE Southwest Symposium on Image Analysis and Interpretation.

[8]  Niels Henze,et al.  Gesture recognition with a Wii controller , 2008, TEI.