Skip to main content
SpringerLink
Log in

Recognition of Action as a Bayesian Parameter Estimation Problem over Time

  • Chapter
Book cover Human Motion

Part of the book series: Computational Imaging and Vision ((CIVI,volume 36))

  • 2872 Accesses

In this chapter we will discuss two problems related to action recognition: The first problem is the one of identifying in a surveillance surveillance scenario to determine walk or run gait and approximate direction. The second problem is concerned with the recovery of action primitives from observed complex actions. Both problems will be discussed within a statistical framework. Bayesian propagation over time offers a framework to treat likelihood observations at each time step and the dynamics between the time steps in a unified manner. The first problem will be approached as a pattern recognition and tracking task by a Bayesian propagation of the likelihoods. The latter problem will be approached by explicitly specifying the dynamics while the likelihood measure will estimate how well each dynamical model fits each time step. Extensive experimental results show the applicability of the Bayesian framework for action recognition and round up our discussion.

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 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 54.99
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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. A. Billard, Y. Epars, S. Calinon, S. Schaal, and G. Cheng. Discovering Optimal Imitation Strategies. Robotics and Autonomous Systems, 47:69-77, 2004.

    Article  Google Scholar 

  2. A. Bobick. Movement, Activity, and Action: The Role of Knowledge in the Perception of Motion. Philosophical Trans. Royal Soc. London, 352:1257-1265, 1997.

    Google Scholar 

  3. A. Bobick. Movements, Activity, and Action: The Role of Knowledge in the Perception of Motion. In Royal Society Workshop on Knowledge-based Vision in Man and Machine, London, February 1997.

    Google Scholar 

  4. A. Bobick and J. Davis. The Recognition of Human Movement Using Temporal Templates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23 (3):257-267, 2001.

    Article  Google Scholar 

  5. H. Bourlard and N. Morgan. Connectionist Speech Recognition: A Hybrid Ap- proach. Kluwer Press, 1994.

    Google Scholar 

  6. G. Bradski and J. Davis. Motion Segmentation and Pose Recognition with Motion History Gradients. Machine Vision and Applications, 13, 2002.

    Google Scholar 

  7. S. Calinon and A. Billard. Stochastic Gesture Production and Recognition Model for a Humanoid Robot. In International Conference on Intelligent Robots and Systems, Alberta, Canada, Aug 2-6, 2005.

    Google Scholar 

  8. S. Calinon, F. Guenter, and A. Billard. Goal-Directed Imitation in a Humanoid Robot. In International Conference on Robotics and Automation, Barcelona, Spain, April 18-22, 2005.

    Google Scholar 

  9. D. Comaniciu, V. Ramesh, and P. Meer. Real-time Tracking of Non-rigid Ob- jects Using mean Shift. In Computer Vision and Pattern Recognition, volume 2, pages 142-149, Hilton Head Island, South Carolina, June 13-15, 2000.

    Google Scholar 

  10. N. Cuntoor and R. Chellappa. Key Frame-Based Activity Representation Using Antieigenvalues. In Asian Conference on Computer Vision, volume 3852 of LNCS, Hyderabad, India, Jan, 13-16, 2006.

    Google Scholar 

  11. B. Dariush. Human Motion Analysis for Biomechanics and Biomedicine. Ma-chine Vision and Applications, 14:202-205, 2003.

    Article  Google Scholar 

  12. A. Doucet, S. Godsill, and C. Andrieu. On Sequential Monte Carlo Sampling Methods for Bayesian Filtering. Statistics and Computing, 10:197-209, 2000.

    Article  Google Scholar 

  13. A. Efros, A. Berg, G. Mori, and J. Malik. Recognizing Action at a Distance. In Internatinal Conference on Computer Vision, Nice, France, Oct 13-16, 2003.

    Google Scholar 

  14. A. Elgammal and L. Davis. Probabilistic Framework for Segmenting People Under Occlusion. In ICCV, ICCV01, 2001.

    Google Scholar 

  15. A. Elgammal and C. Lee. Separating Style and Content on a Nonlinear Manifold. In Computer Vision and Pattern Recognition, Washington DC, June 2004.

    Google Scholar 

  16. A. Elgammal, V. Shet, Y. Yacoob, and L. Davis. Learning Dynamics for Exemplar-based Gesture Recognition. In Computer Vision and Pattern Recog-nition, Madison, Wisconsin, June 16-22, 2003.

    Google Scholar 

  17. M. Giese and T. Poggio. Neural Mechanisms for the Recognition of Biological Movements. Nature Reviews, 4:179-192, 2003.

    Article  Google Scholar 

  18. H. Hermansky. Perceptual Linear Predictive (plp) Analysis of Speech. Journal of Acoustical Society of America, 87(4):1738-1725, 1990.

    Article  Google Scholar 

  19. .X. Huang, Y. Ariki, and M. Jack. Hidden Markov Models for Speech Recognition. Edinburgh University Press, 1990.

    Google Scholar 

  20. X. Huang and M. Jack. Semi-continous Hidden Markov Models for Speech Signals. Computer Speech and Language, 3:239-252, 1989.

    Article  Google Scholar 

  21. A. Ijspeert, J. Nakanishi, and S. Schaal. Movement Imitation withNonlinear Dy-namical Systems in Humanoid Robots. In International Conference on Robotics and Automation, Washington DC, May, 2002.

    Google Scholar 

  22. M. Isard and A. Blake. Condensation - Conditional Density Propagation for Visual Tracking. International Journal of Computer Vision, 29:5-28, 1998.

    Article  Google Scholar 

  23. Y. Ivanov and A. Bobick. Recognition of Visual Activities and Interactions by Stochastic Parsing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):852-872, 2000.

    Article  Google Scholar 

  24. O. Jenkins and M. Mataric. Deriving Action and Behavior Primitives from Human Motion Capture Data. In International Conference on Robotics and Automation, Washington DC, May 2002.

    Google Scholar 

  25. O. Jenkins and M. Mataric. Deriving Action and Behavior Primitives from Human Motion Data. In International Conference on Intelligent Robots and Systems, pages 2551-2556, Lausanne, Switzerland, Sept 30-Oct 4, 2002.

    Google Scholar 

  26. A. Kale, A. Sundaresan, A. Rjagopalan, N. Cuntoor, A. Chowdhury, V. Krueger, and R. Chellappa. Identification of Humans Using Gait. IEEE Transactions on Image Processing, 9:1163-1173, 2004.

    Article  Google Scholar 

  27. G. Kitagawa. Monta Carlo Filter and Smoother for Non-gaussian Nonlinear State Space Models. Journal of Computational and Graphical Statistics, 5:1-25, 1996.

    Article  MathSciNet  Google Scholar 

  28. V. Krueger, J. Anderson, and T. Prehn. Probabilistic Model-based Background Subtraction. In Scandinavian Conference on Image Analysis,, pages 180-187, June 19-22, Joensuu, Finland, 2005.

    Google Scholar 

  29. V. Krueger, J. Anderson, and T. Prehn. Probabilistic Model-based Background Subtraction. In International Conference on Image Analysis and Processing, pages 180-187, Sept. 6-8, Cagliari, Italy, 2005.

    Google Scholar 

  30. B. Li and R. Chellappa. Simultanious Tracking and Verification via Sequential Posterior Estimation. In Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, June 13-15, 2000.

    Google Scholar 

  31. J. Liu and R. Chen. Sequential Monte Carlo for Dynamic Systems. Journal of the American Statistical Association, 93:1031-1041, 1998.

    Google Scholar 

  32. C. Lu and N. Ferrier. Repetitive Motion Analysis: Segmentation and Event Classification. IEEE Transactions on Pattern Analysis and Machine Intelli-gence, 26(2):258-263, 2004.

    Article  Google Scholar 

  33. D. MacKay. In M. Jordan, editor, Learning in Graphical Models, Introduction to Monte Carlo Methods, pages 175-204. MIT Press, 1999.

    Google Scholar 

  34. O. Masound and N. Papanikolopoulos. A Method for Human Action Recogni-toin. Image and Vision Computing, 21:729-743, 2003.

    Article  Google Scholar 

  35. H.-H. Nagel. From Image Sequences Towards Conceptual Descriptions. Image and Vision Computing, 6(2):59-74, 1988.

    Article  Google Scholar 

  36. D. Ormoneit, H. Sidenbladh, M. Black, and T. Hastie. Learning and Track-ing Cyclic Human Motion. In Workshop on Human modelling, Analysis and Synthesis at CVPR, Hilton Head Island, South Carolina, June 13-15 2000.

    Google Scholar 

  37. L. R. Rabiner and B. H. Juang. An introduction to hidden Markov models. IEEE ASSP Magazine, pages 4-15, January 1986.

    Google Scholar 

  38. C. Rao, A. Yilmaz, and M. Shah. View-Invariant Representation and Recogni-tion of Actions. Journal of Computer Vision, 50(2), 2002.

    Google Scholar 

  39. L. Reng, T. Moeslund, and E. Granum. Finding Motion Primitives in Human Body Gestures. In S. Gibet, N. Courty, and J.-F. Kamps, editors, GW 2005, number 3881 in LNAI, pages 133-144. Springer, Berlin Heidelberg, 2006.

    Google Scholar 

  40. L. Reng, T. Moeslund, and E. Granum. Finding motion primitives in human body gestures. In S. Gibet, N. Courty, and J.-F. Kamp, editors, GW 2005, pages 133-144. Springer, 2006.

    Google Scholar 

  41. Y. Ricquebourg and P. Bouthemy. Real-Time Tracking of Moving Persons by Exploiting Spatio-Temporal Image Slices. Transactions on Pattern Analysis and Machine Intelligence, 22(8), 2000.

    Google Scholar 

  42. J. Rittscher, A. Blake, and S. Roberts. Towards the Automatic Analysis of Complex Human Body Motions. Image and Vision Computing, 20, 2002.

    Google Scholar 

  43. G. Rizzolatti, L. Fogassi, and V. Gallese. Parietal Cortex: From Sight to Action. Current Opinion in Neurobiology, 7:562-567, 1997.

    Article  Google Scholar 

  44. G. Rizzolatti, L. Fogassi, and V. Gallese. Neurophysiological Mechanisms Un-derlying the Understanding and Imitation of Action. Nature Reviews, 2:661-670, Sept, 2001.

    Article  Google Scholar 

  45. M. Roh, B. Christmas, J. Kittler, and S. Lee. Robust Player Gesture Spotting and Recognition in Low-Resolution Sports Video. In European Conference on Computer Vision, Graz, Austria, May 7-13, 2006.

    Google Scholar 

  46. S. Schaal. Is Imitation Learning the Route to Humanoid Robots? Trends in Cognitive Sciences, 3(6):233-242, 1999.

    Article  Google Scholar 

  47. A. Stolcke. An Efficient Probabilistic Context-Free Parsing Algorithm That Computes Prefix Probabilities. Computational Linguistics, 21(2):165-201, 1995.

    MathSciNet  Google Scholar 

  48. J. Tenenbaum, V. de Silva, and J. Langford. A Global Geometric Framework for Nonlinear Dimensionality Reduction. Science, 290:2319-2323, 2000.

    Article  Google Scholar 

  49. D. Vecchio, R. Murray, and P. Perona. Decomposition of Human Motiom into Dynamics-based Primitives with Application to Drawing Tasks. Automatica, 39,2003.

    Google Scholar 

  50. S. Zhou, V. Krueger, and R. Chellappa. Probabilistic Recognition of Human Faces From Video. IJCV, 91:214-245, July, 2003.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Vision and Machine Intelligence Lab, CIT, Aalborg University, Lautrupvang 15, 2750, Ballerup, Denmark

    Volker Krüger

Authors
  1. Volker Krüger
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Max-Planck Institute for Computer Science, Stuhlsatzhausenweg 85, D-66123, Saarbrücken, Germany

    Bodo Rosenhahn

  2. The University of Auckland, New Zealand

    Reinhard Klette

  3. Rutgers University, Piscataway, NJ, USA

    Dimitris Metaxas

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer

About this chapter

Cite this chapter

Krüger, V. (2008). Recognition of Action as a Bayesian Parameter Estimation Problem over Time. In: Rosenhahn, B., Klette, R., Metaxas, D. (eds) Human Motion. Computational Imaging and Vision, vol 36. Springer, Dordrecht. https://doi.org/10.1007/978-1-4020-6693-1_3

Download citation

  • DOI: https://doi.org/10.1007/978-1-4020-6693-1_3

  • Publisher Name: Springer, Dordrecht

  • Print ISBN: 978-1-4020-6692-4

  • Online ISBN: 978-1-4020-6693-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation