3-Dimensional Motion Recognition by 4-Dimensional Higher-order Local Auto-correlation

Hiroki Mori, Takaomi Kanda, Dai Hirose, Minoru Asada

2015

Abstract

In this paper, we propose a 4-Dimensional Higher-order Local Auto-Correlation (4D HLAC). The method aims to extract the features of a 3D time series, which is regarded as a 4D static pattern. This is an orthodox extension of the original HLAC, which represents correlations among local values in 2D images and can effectively summarize motion in 3D space. To recognize motion in the real world, a recognition system should exploit motion information from the real-world structure. The 4D HLAC feature vector is expected to capture representations for general 3D motion recognition, because the original HLAC performed very well in image recognition tasks. Based on experimental results showing high recognition performance and low computational cost, we conclude that our method has a strong advantage for 3D time series recognition, even in practical situations.

References

  1. Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on pattern analysis and achine intelligence, pages 679-714.
  2. Chaaraoui, A. A., Padilla-Lopez, J. R., Ferrandez-Postor, F. J., Nieto-Hidalgo, M., and Florenz-Revuelta, F. (2014). A vision-based system for intelligent monitoring: human behaviour analysis and privacy by context. Sensors, 14:8895-8925.
  3. Cherla, S., Kulkarni, K., Kale, A., and Ramasubramanian, V. (2008). Towards fast, view-invariant human action recognition. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition Workshops.
  4. Cilla, R., Patricio, M. A., Berlanga, A., and Molina, J. M. (2013). Human action recognition with sparse classification and multiple-view learning. Expert Systems.
  5. Holte, M., Chakraborty, B., Gonzalez, J., and Moeslund, T. (2012). A local 3-d motion descriptor for multi-view human action recognition from 4-d spatio-temporal interest points. IEEE Journal of Sellected Topics in Signal Process, 6:553-565.
  6. Kanezaki, A., Harada, T., and Kuniyoshi, Y. (2010). Partial matching of real textured 3d objects using color cubic higher-order local auto-correlation features. The Visual Computer, 26(10):1269-1281.
  7. Kobayashi, T. and Otsu, N. (2004). Action and simultaneous multiple-person identification using cubic higherorder local auto-correlation. In Proc. of 17th ICPR, pages 741-744.
  8. Otsu, N. and Kurita, T. (1988). A new scheme for practical flexible and intelligent vision systems. Proceedings of IAPR Workshop on Computer Vision, pages 431-435.
  9. Pehlivan, S. and Duygulu, P. (2010). A new pose-based representation for recognizing actions from multiple cameras. Computer Vision and Image Understanding, 115:140-151.
  10. Turaga, P., Veeraraghavan, A., and Chellappa, R. (2008). Statistical analysis on stiefel and grassmann manifolds with applications in computer vision. In Proc. of the IEEE Conf. on CVPR.
  11. Weinland, D., Ozuysal, M., and Fua, P. (2010). Making action recognition robust to occlusions and viewpoint changes. In Proc. of ECCV.
  12. Weinland, D., Ronfard, R., and Boyer, E. (2006). Free viewpoint action recognition using motion history volumes. Computer Vision and Image Understanding, 104(2-3):249-257.
  13. Wu, X., Xu, D., Duan, L., and Luo, J. (2011). Action recognition using context and appearance distribution features. In Proc. of the IEEE Conf. on CVPR, pages 489-496.
Download


Paper Citation


in Harvard Style

Mori H., Kanda T., Hirose D. and Asada M. (2015). 3-Dimensional Motion Recognition by 4-Dimensional Higher-order Local Auto-correlation . In Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-076-5, pages 223-231. DOI: 10.5220/0005200602230231


in Bibtex Style

@conference{icpram15,
author={Hiroki Mori and Takaomi Kanda and Dai Hirose and Minoru Asada},
title={3-Dimensional Motion Recognition by 4-Dimensional Higher-order Local Auto-correlation},
booktitle={Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2015},
pages={223-231},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005200602230231},
isbn={978-989-758-076-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - 3-Dimensional Motion Recognition by 4-Dimensional Higher-order Local Auto-correlation
SN - 978-989-758-076-5
AU - Mori H.
AU - Kanda T.
AU - Hirose D.
AU - Asada M.
PY - 2015
SP - 223
EP - 231
DO - 10.5220/0005200602230231