Skip to main content
SpringerLink
Log in

A New Framework for View-Invariant Human Action Recognition

  • Chapter
Book cover Robot Intelligence

Part of the book series: Advanced Information and Knowledge Processing ((AI&KP))

Abstract

An exemplar-based view-invariant human action recognition framework is proposed to recognize the human actions from any arbitrary viewpoint image sequence. In this framework, human action is modelled as a sequence of body key poses (i.e., exemplars) which are represented by a collection of silhouette images. The human actions are recognized by matching the observed image sequence to predefined exemplars, in which the temporal constraints are imposed in the exemplar-based Hidden Markov Model (HMM). Furthermore, a new two-level recognition framework is introduced to improve the discrimination capability for the similar human actions. The aim of the first level recognition is to decide an equivalent set in which the testing action is included instead of directly achieving the final recognition results. In the second level, the weighted contour shape feature is used to calculate the observation probability to discriminate the similar actions. The proposed framework is evaluated in a public dataset and the results show that it not only reduces computational complexity, but it is also able to accurately recognize human actions using single cameras. Besides it is verified that the weighted contour shape feature is effective to differentiate the similar arm-related actions.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 169.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Aggarwal, J., Cai, Q.: Human motion analysis: a review. Comput. Vis. Image Underst. 73(3), 428–440 (1999)

    Article  Google Scholar 

  2. Ahmad, M., Lee, S.: Hmm-based human action recognition using multiview image sequences. Proc. Int. Conf. Pattern Recognit. 1, 263–266 (2006)

    Google Scholar 

  3. Anderson, D., Luke, R.H., Keller, J.M., Skubic, M., Rantz, M.J., Aud, M.A.: Modeling human activity from voxel person using fuzzy logic. IEEE Trans. Fuzzy Syst. 17, 39–49 (2009)

    Article  Google Scholar 

  4. Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell. 24(4), 509–522 (2002)

    Article  Google Scholar 

  5. Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. Proc. IEEE Conf. Comput. Vis. 2, 1395–1402 (2005)

    Google Scholar 

  6. Bobick, A., Davis, J.: The recognition of human movement using temporal templates. IEEE Trans. Pattern Anal. Mach. Intell. 23(3), 257–267 (2001)

    Article  Google Scholar 

  7. Chen, H., Chen, H., Chen, Y., Lee, S.: Human action recognition using star skeleton. In: Proc. the 4th ACM International Workshop on Video Surveillance and Sensor Networks, pp. 171–178 (2006)

    Google Scholar 

  8. Cherla, S., Kulkarni, K., Kale, A., Ramasubramanian, V.: Towards fast, view-invariant human action recognition. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2008)

    Google Scholar 

  9. Chan C.S., Liu H.: Fuzzy qualitative human analysis. IEEE Trans. Fuzzy Syst. 17(4), 851–862 (2009)

    Article  MathSciNet  Google Scholar 

  10. Dedeoğlu, Y., Töreyin, B., Güdükbay, U., Çetin, A.: Silhouette-based method for object classification and human action recognition in video. In: Proc. European Conf. Computer Vision, pp. 62–77 (2006)

    Google Scholar 

  11. Elgammal, A., Lee, C.: Inferring 3D body pose from silhouettes using activity manifold learning. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 681–688 (2004)

    Google Scholar 

  12. Elgammal, A., Shet, V., Yacoob, Y., Davis, L.: Learning dynamics for exemplar-based gesture recognition. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 571–578 (2003)

    Google Scholar 

  13. Fathi, A., Mori, G.: Action recognition by learning mid-level motion features. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2008)

    Google Scholar 

  14. Hu, Y., Cao, L., Lv, F., Yan, S., Gong, Y., Huang, T.S.: Action detection in complex scenes with spatial and temporal ambiguities. In: Proc. IEEE Conf. Computer Vision, pp. 1–8 (2009)

    Google Scholar 

  15. Ji, X., Liu, H.: Advances in view-invariant human motion: a review. IEEE Trans. Syst. Man Cybern., Part C, Appl. Rev. 40, 13–24 (2010)

    Google Scholar 

  16. Kale, A., Chowdhury, A., Chellappa, R.: Towards a view invariant gait recognition algorithm. In: Proc. IEEE Conf. Advanced Video and Signal Based Surveillance, pp. 143–150 (2003)

    Google Scholar 

  17. Lee, C., Elgammal, A.: Simultaneous inference of view and body pose using torus manifolds. Proc. Int. Conf. Pattern Recognit. 3, 489–494 (2006)

    Google Scholar 

  18. Li, H., Lin, S., Zhang, Y., Tao, K.: Automatic video-based analysis of athlete action. In: Proc. IEEE Conf. Image Analysis and Processing, pp. 205–210 (2007)

    Google Scholar 

  19. Liu, H.: A fuzzy qualitative framework for connecting robot qualitative and quantitative representations. IEEE Trans. Fuzzy Syst. 16(6), 1522–1530 (2008)

    Article  Google Scholar 

  20. Liu, J., Ali, S., Shah, M.: Recognizing human actions using multiple features. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2008)

    Google Scholar 

  21. Lv, F., Nevatia, R.: Recognition and segmentation of 3-D human action using HMM and multi-class AdaBoost. In: Proc. European Conf. Computer Vision, vol. 4, pp. 359–372 (2006)

    Google Scholar 

  22. Lv, F., Nevatia, R.: Single view human action recognition using key pose matching and Viterbi path searching. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2007)

    Google Scholar 

  23. Mori, T., Segawa, Y., Shimosaka, M., Sato, T.: Hierarchical recognition of daily human actions based on Continuous Hidden Markov Models. In: Proc. IEEE Conf. Automatic Face and Gesture Recognition, pp. 779–784 (2004)

    Google Scholar 

  24. Natarajan, P., Nevatia, R.: View and scale invariant action recognition using multiview shape-flow models. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2008)

    Google Scholar 

  25. Ning, H., Xu, W., Gong, Y., Huang, T.: Latent pose estimator for continuous action recognition. In: Proc. European Conf. Computer Vision, pp. 1–7 (2008)

    Google Scholar 

  26. Ogale, A., Karapurkar, A., Aloimonos, Y.: View-invariant modeling and recognition of human actions using grammars. Proc. IEEE Conf. Comput. Vis 5, 115–126 (2005)

    Google Scholar 

  27. Ong, E., Micilotta, A., Bowden, R., Hilton, A.: Viewpoint invariant exemplar-based 3D human tracking. Comput. Vis. Image Underst. 104(2–3), 178–189 (2006)

    Article  Google Scholar 

  28. Parameswaran, V., Chellappa, R.: View invariants for human action recognition. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 83–101 (2003)

    Google Scholar 

  29. Parameswaran, V., Chellappa, R.: View independent human body pose estimation from a single perspective image. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 16–22 (2004)

    Google Scholar 

  30. Patrick, P., Vand Geoff Svetha, W.: Tracking as recognition for articulated full body human motion analysis. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2007)

    Google Scholar 

  31. Rao, C., Yilmaz, A., Shah, M.: View-Invariant representation and recognition of actions. Int. J. Comput. Vis. 50(2), 203–226 (2002)

    Article  MATH  Google Scholar 

  32. Ribeiro, P., Santos-Victor, J., Lisboa, P.: Human activity recognition from video: modeling, feature selection and classification architecture. In: Proc. Int Workshop. Human Activity Recognition and Modelling, pp. 1–10 (2005)

    Google Scholar 

  33. Rittscher, J., Blake, A., Roberts, S.: Towards the automatic analysis of complex human body motions. Image Vis. Comput. 20(12), 905–916 (2002)

    Article  Google Scholar 

  34. Rogez, G., Guerrero, J., Martınez, J., Orrite, C.: Viewpoint independent human motion analysis in man-made environments. In: Proc. British Machine Vision Conference, pp. 659–668 (2006)

    Google Scholar 

  35. Shi, Y., Bobick, A., Essa, I.: Learning temporal sequence model from partially labeled data. In: Computer Vision and Pattern Recognition, pp. 1631–1638 (2006)

    Google Scholar 

  36. Sminchisescu, C., Kanaujia, A., Metaxas, D.: Conditional models for contextual human motion recognition. Comput. Vis. Image Underst. 104(2–3), 210–220 (2006)

    Article  Google Scholar 

  37. Sutton, C., McCallum, A., Rohanimanesh, K.: Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data. J. Mach. Learn. Res. 8, 693–723 (2007)

    MATH  Google Scholar 

  38. Toyama, K., Blake, A.: Probabilistic tracking with exemplars in a metric space. Int. J. Comput. Vis. 48, 9–19 (2002)

    Article  MATH  Google Scholar 

  39. Ullah, F., Kaneko, S.: Using orientation codes for rotation-invariant template matching. Pattern Recognit. 37(2), 201–209 (2004)

    Article  MATH  Google Scholar 

  40. Wang, L., Suter, D.: Recognizing human activities from silhouettes: motion subspace and factorial discriminative graphical model. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2007)

    Google Scholar 

  41. Wang, S., Quattoni, A., Morency, L., Demirdjian, D., Darrell, T.: Hidden conditional random fields for gesture recognition. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 1521–1527 (2006)

    Google Scholar 

  42. Weinland, D., Grenoble, F., Boyer, E., Ronfard, R., Inc, A.: Action recognition from arbitrary views using 3D exemplars. In: Proc. IEEE Conf. Computer Vision, pp. 1–7 (2007)

    Google Scholar 

  43. Weinland, D., Ronfard, R., Boyer, E.: Free viewpoint action recognition using motion history volumes. Comput. Vis. Image Underst. 104, 249–257 (2006)

    Article  Google Scholar 

  44. Yan, P., Khan, S., Shah, M.: Learning 4D action feature models for arbitrary view action recognition. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 12, pp. 1–8 (2008)

    Google Scholar 

  45. Yang, Y., Hao, A., Zhao, Q.: View-invariant action recognition using interest points. In: Proc. Int. Conf. Multimedia Information Retrieval, pp. 305–312 (2008)

    Google Scholar 

  46. Yilmaz, A., Shah, M.: Actions as objects: a novel action representation. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 984–989 (2005)

    Google Scholar 

  47. Yu, H., Sun, G., Song, W., Li, X.: Human motion recognition based on neural network. In: Proc. IEEE Conf. Communications, Circuits and Systems, vol. 2, pp. 977–982 (2005)

    Google Scholar 

  48. Yu, S., Tan, D., Tan, T.: Modelling the effect of view angle variation on appearance-based gait recognition. In: Proc. Asian Conf. Computer Vision, vol. 1, pp. 807–816 (2006)

    Google Scholar 

  49. Zhang, J., Gong, S.: Action categorization with modified hidden conditional random field. Pattern Recognit. 43, 197–203 (2010)

    Article  MATH  Google Scholar 

Download references

Acknowledgements

The authors would like to thank Dr. Weinland et al. for kindly providing the INRIA IXMAS dataset.

Author information

Authors and Affiliations

    Authors
    1. Xiaofei Ji
      View author publications

      You can also search for this author in PubMed Google Scholar

    2. Honghai Liu
      View author publications

      You can also search for this author in PubMed Google Scholar

    3. Yibo Li
      View author publications

      You can also search for this author in PubMed Google Scholar

    Corresponding author

    Correspondence to Xiaofei Ji .

    Editor information

    Editors and Affiliations

    1. School of Creative Technologies, The University of Portsmouth, Portsmouth, PO1 2DJ, United Kingdom

      Honghai Liu

    2. Department of Computer Science, University of Essex, Wivenhoe Park, United Kingdom

      Dongbing Gu

    3. , School of Engineering, University of Brighton, Moulsecoomb, Brighton, BN2 4GJ, United Kingdom

      Robert J. Howlett

    4. Department of Computer Science, University of Wales, Aberystwyth, SY23 3DB, United Kingdom

      Yonghuai Liu

    Rights and permissions

    Reprints and permissions

    Copyright information

    © 2010 Springer-Verlag London Limited

    About this chapter

    Cite this chapter

    Ji, X., Liu, H., Li, Y. (2010). A New Framework for View-Invariant Human Action Recognition. In: Liu, H., Gu, D., Howlett, R., Liu, Y. (eds) Robot Intelligence. Advanced Information and Knowledge Processing. Springer, London. https://doi.org/10.1007/978-1-84996-329-9_4

    Download citation

    • DOI: https://doi.org/10.1007/978-1-84996-329-9_4

    • Publisher Name: Springer, London

    • Print ISBN: 978-1-84996-328-2

    • Online ISBN: 978-1-84996-329-9

    • eBook Packages: Computer ScienceComputer Science (R0)

    Publish with us

    Policies and ethics

    Search

    Navigation