SPARSE REPRESENTATIONS AND INVARIANT SEQUENCE-FEATURE EXTRACTION FOR EVENT DETECTION

Alexandru P. Condurache, Alfred Mertins

Abstract

We address the problem of detecting unusual actions performed by a human in a video. Broadly speaking, we achieve our goal by matching the observed action to a set of a-priori known actions. If the observed action can not be matched to any of the known actions (representing the normal case), we conclude that an event has taken place. In this contribution we will show how sparse representations of actions can be used for event detection. Our input data are video sequences showing different actions. Special care is taken to extract features from these sequences. The features are chosen such that the sparse-representations paradigm can be applied and they exhibit a set of invariance properties needed for detecting unusual human actions. We test our methods on sequences showing different people performing various actions such as walking or running.

References

  1. Arbter, K., Snyder, W., Burkhardt, H., and Hirzinger, G. (1990). Application of affine-invariant fourier descriptors to recognition of 3-d objects. IEEE Trans. Patt. Anal. Mach. Intell., 12:640-647.
  2. Candès, E. and Tao, T. (2006). Near-optimal signal recovery from random projections: Universal encoding strategies? IEEE Trans. Inform. Theory, 52(12):5406- 5425.
  3. d'Aspremont, A., Ghaoui, L. E., Jordan, M., and Lanckriet, G. (2007). A direct formulation of sparse pca using semidefinite programming. SIAM Review, 49(3).
  4. Donoho, D. (2006). Compressed sensing. IEEE Trans. Inform. Theory, 52(4):1289-1306.
  5. Donoho, D. and Elad, M. (2003). Optimal sparse representation in general (nonorthogonal) dictionaries via 1 minimization. Proc. Nat'l Academy of Sciences, pages 2197-2202.
  6. Gorelick, L., Blank, M., Shechtman, E., Irani, M., and Basri, R. (2007). Actions as space-time shapes. Trans. Patt. Anal. Mach. Intell., 29(12):2247-2253.
  7. Guo, K., Ishwar, P., and Konrad, J. (2010). Action recognition using sparse representation on covariance manifolds of optical flow. In Proc. AVSS, pages 188-195.
  8. Matern, D., Condurache, A. P., and Mertins, A. (2011). Event detection using log-linear models for coronary contrast agent injections. In Proc. ICPRAM.
  9. Müller, F. and Mertins, A. (2011). Contextual invariantintegration features for improved speaker-independent speech recognition. Speech Comm., 53(6):830 - 841.
  10. Otsu, N. (1979). A threshold selection method from graylevel histograms. IEEE Trans. on Sys., Man and Cyb., SMC-9(1):62-66.
  11. Schuldt, C., Laptev, I., and Caputo, B. (2004). Recognizing human actions: A local svm approach. Proc. ICPR, 3:32-36.
  12. Schulz-Mirbach, H. (1992). On the existence of complete invariant feature spaces in pattern recognition. In Proc. ICPR, volume 2, pages 178-182, The Hague.
  13. Schulz-Mirbach, H. (1994). Algorithms for the construction of invariant features. In DAGM Symposium, volume 5, pages 324-332, Wien.
  14. Wright, J., Yang, A., Ganesh, A., Sastry, S., and Ma, Y. (2009). Robust face recognition via sparse representation. IEEE Trans. Patt. Anal. Mach. Intell., 31(2):210- 227.
  15. Yang, A., Jafari, R., Sastry, S., and Bajcsy, R. (2008). Distributed recognition of human actions using wearable motion sensor networks. J Amb. Intl. Smt. Env., 30(5):893-908.
Download


Paper Citation


in Harvard Style

P. Condurache A. and Mertins A. (2012). SPARSE REPRESENTATIONS AND INVARIANT SEQUENCE-FEATURE EXTRACTION FOR EVENT DETECTION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 679-684. DOI: 10.5220/0003817906790684


in Bibtex Style

@conference{visapp12,
author={Alexandru P. Condurache and Alfred Mertins},
title={SPARSE REPRESENTATIONS AND INVARIANT SEQUENCE-FEATURE EXTRACTION FOR EVENT DETECTION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={679-684},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003817906790684},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - SPARSE REPRESENTATIONS AND INVARIANT SEQUENCE-FEATURE EXTRACTION FOR EVENT DETECTION
SN - 978-989-8565-03-7
AU - P. Condurache A.
AU - Mertins A.
PY - 2012
SP - 679
EP - 684
DO - 10.5220/0003817906790684