Combining body sensors and visual sensors for motion training

ABSTRACT

We present a new framework to build motion training systems using machine learning techniques. The goal of our approach is the design of a training method based on the combination of body and visual sensors. We introduce the concept of a Motion Chunk to analyze human motion and construct a motion data model in real-time. The system provides motion detection and evaluation and visual feedback generation. We discuss the results of user tests regarding the system efficiency in martial art training. With our system, trainers can generate motion training videos and practice complex motions precisely evaluated by a computer.

REFERENCES

• 1: J. K. Aggarwal , Sangho Park, Human Motion: Modeling and Recognition of Actions and Interactions, Proceedings of the 3D Data Processing, Visualization, and Transmission, 2nd International Symposium on (3DPVT'04), p.640-647, September 06-09, 2004 [doi>10.1109/3DPVT.2004.75]
• 2: S. Baek, S. Lee, and G. Kim. Motion retargeting and evaluation for vr-based training of free motions. The Visual Computer, 19(4):222--242, July 2003.
• 3: L. Bao and S. Intille. Activity recognition from user-annotated acceleration data. In Proceedings of Pervasive 2004, volume LNCS 3001, pages 1--17, 2004.
• 4: D. Becker. Sensei: A real-time recognition, feedback, and training system for t'ai chi gestures. Master's thesis, Massachusetts Institute of Technology, 1997.
• 5: G. S. Chambers, S. Venkatesh, G. West, and H. Bui. Hierarchical recognition of intentional human gestures for sports video annotation. In Proceedings of ICPR02, pages 1082--1085, Thessaloniki, Greece, September 2002.
• 6: Philo Tan Chua , Rebecca Crivella , Bo Daly , Ning Hu , Russ Schaaf , David Ventura , Todd Camill , Jessica Hodgins , Randy Pausch, Training for Physical Tasks in Virtual Environments: Tai Chi, Proceedings of the IEEE Virtual Reality 2003, p.87, March 22-26, 2003
• 7: J. W. Davis and A. F. Bobick. Virtual pat: A virtual personal aerobics trainer. In Proceedings of Workshop on Perceptual User Interfaces, pages 13--18, November 1998.
• 8: Deborah Estrin , David Culler , Kris Pister , Gaurav Sukhatme, Connecting the Physical World with Pervasive Networks, IEEE Pervasive Computing, v.1 n.1, p.59-69, January 2002 [doi>10.1109/MPRV.2002.993145]
• 9: M. Gross, S. Wuermlin, M. Naef, E. Lamboraz, C. Spagno, A. Kunz, E. Koller-Meier, T. Svoboda, L. V. Gool, S. Lang, K. Strehlke, A. V. Moere, and O. Staadt. blue-c: A spatially immersive display and 3d video portal for telepresence. In Proceedings of ACM SIGGRAPH 2003, pages 819--827, 2003.
• 10: L. Rabiner. A tutorial on hidden markov models and selected applications in speech recognition. In Proceedings of the IEEE, volume 77, pages 257--286, Feburuary 1989.
• 11: Xin Wei Sha , Giovanni Iachello , Steven Dow , Yoichiro Serita , Tazama St. Julien , Julien Fistre, Continuous Sensing of Gesture for Control of Audio-Visual Media, Proceedings of the 7th IEEE International Symposium on Wearable Computers, p.236, October 21-23, 2003
• 12: T. Starner and A. Pentland. Visual Recognition of American Sign Language Using Hidden Markov Models. M.I.T. Media Laboratory, Cambridge MA.
• 13: Masami Takahata , Kensuke Shiraki , Yutaka Sakane , Yoichi Takebayashi, Sound feedback for powerful karate training, Proceedings of the 2004 conference on New interfaces for musical expression, p.13-18, June 03-05, 2004, Hamamatsu, Shizuoka, Japan
• 14: U. Yang. Just follow me: An immersive vr-based motion training system. In Proceedings of International Conference on Virtual Systems and Multimedia, 1999.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.1 Multimedia Information Systems

Additional Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.6 Methodology and Techniques
          Subjects: Interaction techniques

Keywords:
body sensor, motion analysis, motion chunk, motion training system, visual feedback, visual sensor