Human Action Recognition for Real-time Applications

Ivo Reznicek, Pavel Zemcik

2014

Abstract

Action recognition in video is an important part of many applications. While the performance of action recognition has been intensively investigated, not much research so far has been done in the understanding of how long a sequence of video frames is needed to correctly recognize certain actions. This paper presents a new method of measurement of the length of the video sequence necessary to recognize the actions based on space-time feature points. Such length is the key information necessary to successfully recognize the actions in real-time or performance critical applications. The action recognition used in the presented approach is the state-of-the-art one; vocabulary, bag of words and SVM processing. The proposed methods is experimentally evaluated on human action recognition dataset.

References

  1. Csurka, G., Dance, C. R., Fan, L., Willamowski, J., and Bray, C. (2004). Visual categorization with bags of keypoints. In In Workshop on Statistical Learning in Computer Vision, ECCV, pages 1-22.
  2. Dalal, N., Triggs, B., and Schmid, C. (2006). Human detection using oriented histograms of flow and appearance. In Proceedings of the 9th European conference on Computer Vision - Volume Part II, ECCV'06, pages 428-441, Berlin, Heidelberg. Springer-Verlag.
  3. Duda, R. O., Hart, P. E., and Stork, D. G. (2000). Pattern Classification (2nd Edition). Wiley-Interscience.
  4. Hsu, C.-W., chung Chang, C., and jen Lin, C. (2010). A practical guide to support vector classification.
  5. Jain, M., Jégou, H., and Bouthemy, P. (2013). Better exploiting motion for better action recognition. In CVPR - International Conference on Computer Vision and Pattern Recognition, Portland, Ótats-Unis.
  6. Jegou, H., Perronnin, F., Douze, M., Sanchez, J., Perez, P., and Schmid, C. (2012). Aggregating local image descriptors into compact codes. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 34(9):1704-1716.
  7. Laptev, I. and Lindeberg, T. (2003). Space-time interest points. In IN ICCV, pages 432-439.
  8. Le, Q., Zou, W., Yeung, S., and Ng, A. (2011). Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 3361-3368.
  9. Lowe, D. G. (2004). Distinctive image features from scaleinvariant keypoints. Int. J. Comput. Vision, 60(2):91- 110.
  10. Marszalek, M., Laptev, I., and Schmid, C. (2009). Actions in context. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 2929-2936.
  11. Reznicek, I. and Zemcik, P. (2013). Action recognition using combined local features. In Proceedings of the IADIS Computer graphics, Visulisation, Coputer Vision and Image Processing 2013, pages 111-118. IADIS.
  12. Ullah, M. M., Parizi, S. N., and Laptev, I. (2010). Improving bag-of-features action recognition with nonlocal cues. In Proceedings of the British Machine Vision Conference, pages 95.1-95.11. BMVA Press. doi:10.5244/C.24.95.
  13. Wang, H., Klaser, A., Schmid, C., and Liu, C.-L. (2011). Action recognition by dense trajectories. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 3169-3176.
  14. Zhang, J., Marszalek, M., Lazebnik, S., and Schmid, C. (2006). Local features and kernels for classification of texture and object categories: A comprehensive study. In Computer Vision and Pattern Recognition Workshop, 2006. CVPRW 7806. Conference on, pages 13-13.
  15. Zhang, Z. (2012). Microsoft kinect sensor and its effect. MultiMedia, IEEE, 19(2):4-10.
Download


Paper Citation


in Harvard Style

Reznicek I. and Zemcik P. (2014). Human Action Recognition for Real-time Applications . In Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-018-5, pages 646-653. DOI: 10.5220/0004826606460653


in Bibtex Style

@conference{icpram14,
author={Ivo Reznicek and Pavel Zemcik},
title={Human Action Recognition for Real-time Applications},
booktitle={Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2014},
pages={646-653},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004826606460653},
isbn={978-989-758-018-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Human Action Recognition for Real-time Applications
SN - 978-989-758-018-5
AU - Reznicek I.
AU - Zemcik P.
PY - 2014
SP - 646
EP - 653
DO - 10.5220/0004826606460653