RECOGNIZING USER INTERFACE CONTROL GESTURES FROM ACCELERATION DATA USING TIME SERIES TEMPLATES

Pekka Siirtola, Perttu Laurinen, Heli Koskimäki, Juha Röning

2010

Abstract

This study presents a method for recognizing six predefined gestures using data collected with a wrist-worn triaxial accelerometer. The aim of the study is to design a gesture recognition-based control system for a simple user interface. The recognition is done by matching the shapes that user’s movements cause to acceleration signals to predefined time series templates describing gestures. In this study matching is done by using three different trajectory distance measures, the results show that the weighted double fold gives the best results. The superiority of this distance measure was shown using a statistical significance test. A user-dependent version of the method recognizes gestures with accuracy of 94.3% and a recognition rate of the user-independent version is 85.5%. This work was supported by the EU 6th Framework Program Project XPRESS.

References

  1. Corradini, A. (2001). Dynamic time warping for off-line recognition of a small gesture vocabulary. In RATFGRTS 7801: Proceedings of the IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, page 82, Washington, DC, USA. IEEE Computer Society.
  2. Gupta, L., Molfese, D., Tammana, R., and Simos, P. (1996). Nonlinear alignment and averaging for estimating the evoked potential. Biomedical Engineering, IEEE Transactions on, 43(4):348-356.
  3. Ko, M., West, G., Venkatesh, S., and Kumar, M. (2008). Using dynamic time warping for online temporal fusion in multisensor systems. Inf. Fusion, 9(3):370-388.
  4. Laurinen, P., Siirtola, P., and Röning, J. (2006). Efficient algorithm for calculating similarity between trajectories containing an increasing dimension. pages 392-399. Proc. 24th IASTED international conference on Artificial intelligence and applications, February 13 - 16, Innsbruck, Austria.
  5. Niennattrakul, V. and Ratanamahatana, C. (2007). Inaccuracies of shape averaging method using dynamic time warping for time series data. In ICCS 7807: Proceedings of the 7th international conference on Computational Science, Part I, pages 513-520, Berlin, Heidelberg. Springer-Verlag.
  6. Siirtola, P., Laurinen, P., and Röning, J. (2008). A weighted distance measure for calculating the similarity of sparsely distributed trajectories. In ICMLA'08: Proceedings of the Seventh International Conference on Machine Learning and Applications.
  7. Siirtola, P., Laurinen, P., and Röning, J. (2009). Mining an optimal prototype from a periodic time series: an evolutionary computation-based approach. In Congress on Evolutionary Computation (CEC 2009), pages 2818-2824.
  8. Stiefmeier, T. and Roggen, D. (2007). Gestures are strings: Efficient online gesture spotting and classification using string matching. In In: Proceedings of 2nd International Conference on Body Area Networks (BodyNets).
Download


Paper Citation


in Harvard Style

Siirtola P., Laurinen P., Koskimäki H. and Röning J. (2010). RECOGNIZING USER INTERFACE CONTROL GESTURES FROM ACCELERATION DATA USING TIME SERIES TEMPLATES . In Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO, ISBN 978-989-8425-02-7, pages 176-182. DOI: 10.5220/0002899601760182


in Bibtex Style

@conference{icinco10,
author={Pekka Siirtola and Perttu Laurinen and Heli Koskimäki and Juha Röning},
title={RECOGNIZING USER INTERFACE CONTROL GESTURES FROM ACCELERATION DATA USING TIME SERIES TEMPLATES},
booktitle={Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,},
year={2010},
pages={176-182},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002899601760182},
isbn={978-989-8425-02-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,
TI - RECOGNIZING USER INTERFACE CONTROL GESTURES FROM ACCELERATION DATA USING TIME SERIES TEMPLATES
SN - 978-989-8425-02-7
AU - Siirtola P.
AU - Laurinen P.
AU - Koskimäki H.
AU - Röning J.
PY - 2010
SP - 176
EP - 182
DO - 10.5220/0002899601760182