Advertisement

Machine Vision and Applications

, Volume 21, Issue 3, pp 377–389 | Cite as

Human action detection via boosted local motion histograms

  • Qingshan LuoEmail author
  • Xiaodong Kong
  • Guihua Zeng
  • Jianping Fan
Short Paper

Abstract

This paper presents a novel learning method for human action detection in video sequences. The detecting problem is not limited in controlled settings like stationary background or invariant illumination, but studied in real scenarios. Spatio-temporal volume analysis for actions is adopted to solve the problem. To develop effective representation while remaining resistant to background motions, only motion information is exploited to define suitable descriptors for action volumes. On the other hand, action models are learned by using boosting techniques to select discriminative features for efficient classification. This paper also shows how the proposed method enables learning efficient action detectors, and validates them on publicly available datasets.

Keywords

Action retrieving Activity analysis Video understanding Visual surveillance Local motion histograms 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dalal N., Triggs B.: Histograms of oriented gradients for human detection. Comput. Vis. Pattern Recognit. 2, 886–893 (2005)Google Scholar
  2. 2.
    Dalal N., Triggs B., Schmid C.: Human detection using oriented histograms of flow and appearance. Eur. Conf. Comput. Vis. 2, 428–441 (2006)Google Scholar
  3. 3.
    Dollár, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: VS-PETS, pp. 65–72 (2005)Google Scholar
  4. 4.
    Friedman J., Hastie T., Tibshirani R.: Additive logistic regression: A statistical view of boosting. Ann. Stat. 38(2), 337–374 (2000)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Gavrila D.M.: The visual analysis of human movement: A survey. Comput. Vis. Image Underst. 73(1), 82–98 (1999)zbMATHCrossRefGoogle Scholar
  6. 6.
    Gennert, M.A., Negahdaripour, S.: Relaxing the brightness constancy assumption in computing optical flow. A.I. Memo, p. 975. MIT Press, Cambridge (1987)Google Scholar
  7. 7.
    Horn B.K., Schunck B.G.: Determining optical flow. Artif. Intell. 17, 185–203 (1981)CrossRefGoogle Scholar
  8. 8.
    Ke Y., Sukthankar R., Hebert M.: Efficient visual event detection using volumetric features. IEEE Int. Conf. Comput. Vis. 1, 166–173 (2005)Google Scholar
  9. 9.
    Kim, T.K., Wong, S.F., Cipolla, R.: Tensor canonical correlation analysis for action classification. In: CVPR (2007)Google Scholar
  10. 10.
    Laptev, I.: Improvements of object detection using boosted histograms. In: BMVC, vol. 3, pp. 949–958 (2006)Google Scholar
  11. 11.
    Laptev I., Lindeberg T.: Space-time interest points. IEEE Int. Conf. Comput. Vis. 1, 432–439 (2003)CrossRefGoogle Scholar
  12. 12.
    Laptev, I., Pérez, P.: Retrieving actions in movies. IEEE Int. Conf. Comput. Vis., pp. 432–439 (2007)Google Scholar
  13. 13.
    Lienhart, R., Kuranov, A., Pisarevsky, V.: Empirical analysis of detection cascades of boosted classifiers for rapid object detection. MRL technical report (2002)Google Scholar
  14. 14.
    Niebles, J.C., Wang, H., Li, F.F.: Unsupervised learning of human action categories using spatial-temporal words. In: BMVC (2006)Google Scholar
  15. 15.
    Porikli F.: Integral histogram: A fast way to extract histograms in cartesian spaces. Comput. Vis. Pattern Recognit. 1, 829–836 (2005)Google Scholar
  16. 16.
    Proesmans, M., Gool, L.J.V., Pauwels, E.J., Oosterlinck, A.: Determination of optical flow and its discontinuities using non-linear diffusion. In: European Conference on Computer Vision, pp. 295–304. Springer, London (1994)Google Scholar
  17. 17.
    Ramanan, D., Forsyth, D.A.: Automatic annotation of everyday movements. In: Advances in Neural Information Processing Systems, vol. 16. MIT Press, Cambridge (2004)Google Scholar
  18. 18.
    Schuldt C., Laptev I., Caputo B.: Recognizing human actions: A local svm approach. Int. Conf. Pattern Recognit. 3, 32–36 (2004)Google Scholar
  19. 19.
    Shah M., Jain R.: Motion-Based Recognition. Computational Imaging and Vision Series. Kluwer, Dordrecht (1997)Google Scholar
  20. 20.
    Viola P., Jones M.: Rapid object detection using a boosted cascade of simple features. Comput. Vis. Pattern Recognit. 1, 511–518 (2001)Google Scholar
  21. 21.
    Wong, S.F., Kim, T.K., Cipolla, R.: Learning motion categories using both semantic and structural information. In: CVPR (2007)Google Scholar
  22. 22.
    Yilmaz A., Shah M.: Recognizing human actions in videos acquired by uncalibrated moving cameras. IEEE Int. Conf. Comput. Vis. 1, 150–157 (2005)Google Scholar

Copyright information

© Springer-Verlag 2008

Authors and Affiliations

  • Qingshan Luo
    • 1
    Email author
  • Xiaodong Kong
    • 1
  • Guihua Zeng
    • 1
  • Jianping Fan
    • 2
  1. 1.Department of Electronic EngineeringShanghai Jiaotong UniversityShanghaiChina
  2. 2.Department of Computer ScienceUniversity of North Carolina at CharlotteCharlotteUSA

Personalised recommendations