Skip to main content
SpringerLink
Log in

Evaluating Manifold Learning Methods and Discriminative Sequence Classifiers in View-Invariant Action Recognition

  • Conference paper
User-Centric Technologies and Applications

Part of the book series: Advances in Intelligent and Soft Computing ((AINSC,volume 94))

  • 321 Accesses

Abstract

This paper evaluates the accuracy of Isometric Projections and Hidden Conditional Random Fields in the view invariant Recognition of Human Actions. Silhouette sequences captured from different viewpoints are projected into a low dimensional manifold using Isometric Projections. The projected sequences are used to train a hidden conditional random field for action classification. The system is evaluated using sequences captured by a camera not used during training. The accuracy of the system is measured using the IXMAS dataset on the experiments.

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 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

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. Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural computation 15(6), 1373–1396 (2003)

    Article  MATH  Google Scholar 

  2. Bobick, A.F., Davis, J.W.: The recognition of human movement using temporal templates. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(3), 257–267 (2001)

    Article  Google Scholar 

  3. Cai, D., He, X., Han, J.: Isometric projection. In: Proceedings of the National Conference on Artificial Intelligence, vol. 22, p. 528. AAAI Press, MIT Press, Menlo Park, CA, Cambridge, MA, London (1999)

    Google Scholar 

  4. Gritai, A., Sheikh, Y., Shah, M.: On the use of anthropometry in the invariant analysis of human actions. In: Proceedings of the 17th International Conference on Pattern Recognition (ICPR 2004), vol. 2, pp. 923–926 (2004)

    Google Scholar 

  5. He, X., Niyogi, P.: Locality Preserving Projections. In: NIPS (2003)

    Google Scholar 

  6. Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: International Conference on Machine Learning (2001)

    Google Scholar 

  7. Lavee, G., Rivlin, E., Rudzsky, M.: Understanding Video Events: A Survey of Methods for Automatic Interpretation of Semantic Occurrences in Video. IEEE Transactions on Systems, Man and Cybernetics - Part C: Applications and Reviews 39(5), 489–504 (2009)

    Article  Google Scholar 

  8. Lewandowski, M., Makris, D., Nebel, J.C.: View and Style-Independent Action Manifolds for Human Activity Recognition. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 547–560. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  9. Lv, F., Nevatia, R.: Single view human action recognition using key pose matching and viterbi path searching. In: IEEE Conference on Computer Vision and Pattern Recognition, 2007 (CVPR 2007), pp. 1–8. IEEE, Los Alamitos (2007)

    Google Scholar 

  10. Martínez-Contreras, F., Orrite-Uruñuela, C., Herrero-Jaraba, E., Ragheb, H., Velastin, S.A.: Recognizing Human Actions using Silhouette-based HMM. In: IEEE Conference on Advanced Video and Signal-based Surveillance, pp. 43–48 (2009)

    Google Scholar 

  11. Mendoza, M., Pérez De La Blanca, N.: Applying space state models in human action recognition: a comparative study. Articulated Motion and Deformable Objects, 53–62 (2008)

    Google Scholar 

  12. Parameswaran, V., Chellappa, R.: View invariants for human action recognition. In: Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003, vol. 2 (2003)

    Google Scholar 

  13. Peng, B., Qian, G., Rajko, S.: View-Invariant Full-Body Gesture Recognition via Multilinear Analysis of Voxel Data. In: Third ACM/IEEE Conference on Distributed Smart Cameras (September,2009)

    Google Scholar 

  14. Poppe, R.: A survey on vision-based human action recognition. Image and Vision Computing 28(6), 976–990 (2010)

    Article  Google Scholar 

  15. Quattoni, A., Wang, S., Morency, L.-P., Collins, M., Darrell, T.: Hidden conditional random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(10), 1848–1852 (2007)

    Article  Google Scholar 

  16. Rao, C., Yilmaz, A., Shah, M.: View-invariant representation and recognition of actions. International Journal of Computer Vision 50(2), 203–226 (2002)

    Article  MATH  Google Scholar 

  17. Richard, S., Kyle, P.: Viewpoint Manifolds for Action Recognition. EURASIP Journal on Image and Video Processing (2009)

    Google Scholar 

  18. Sheikh, Y., Sheikh, M., Shah, M.: Exploring the space of a human action. In: Tenth IEEE International Conference on Computer Vision, 2005 (ICCV 2005), vol. 1 (2005)

    Google Scholar 

  19. Tenenbaum, J.B., Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319 (2000)

    Article  Google Scholar 

  20. Tran, D., Sorokin, A., Forsyth, D.: Human activity recognition with metric learning. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 548–561. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  21. Turaga, P., Chellappa, R., Subrahmanian, V.S., Udrea, O.: Machine Recognition of Human Activities: A Survey. IEEE Transactions on Circuits and Systems for Video Technology 18(11), 1473–1488 (2008)

    Article  Google Scholar 

  22. Turaga, P., Veeraraghavan, A., Chellappa, R.: Statistical analysis on Stiefel and Grassmann manifolds with applications in computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8. IEEE, Los Alamitos (2008)

    Google Scholar 

  23. Weinland, D., Boyer, E., Ronfard, R.: Action recognition from arbitrary views using 3d exemplars. In: IEEE 11th International Conference on Computer Vision, 2007(ICCV 2007), pp. 1–7. IEEE, Los Alamitos (2007)

    Chapter  Google Scholar 

  24. Weinland, D., Ronfard, R., Boyer, E.: Free viewpoint action recognition using motion history volumes. Computer Vision and Image Understanding 104(2-3), 249–257 (2006)

    Article  Google Scholar 

  25. Zhang, J., Gong, S.: Action categorization with modified hidden conditional random field. Pattern Recognition 43(1), 197–203 (2010)

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Science Deparment, Universidad Carlos III de Madrid, Avda. de la Universidad Carlos III, 22, 28270, Colmenarejo, Madrid, Spain

    Rodrigo Cilla, Miguel A. Patricio, Antonio Berlanga & José M. Molina

Authors
  1. Rodrigo Cilla
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Miguel A. Patricio
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Antonio Berlanga
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. José M. Molina
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Departamento de Informática Escuela Politécnica Superior (campus de Colmenarejo), Universidad Carlos III de Madrid , Avda. Universidad Carlos III, 22, 28270, Colmenarejo (MADRID), Spain

    José M. Molina

  2. Departamento de Señales, Sistemas y diocomunicaciones ETSI Telecomunicación , Universidad Politécnica de Madrid, Av. Complutense 30, 28040, Madrid, Spain

    José Ramón Casar Corredera

  3. Departamento de Ciencias de la Computación Escuela Politécnica , Universidad de Alcalá, 28806, Alcalá de Henares, Madrid, Spain

    Manuel Felipe Cátedra Pérez

  4. Departamento de Tecnología Electrónica y de las Comunicaciones Escuela Politécnica Superior , Universidad Autónoma de Madrid, c/ Francisco Tomás y Valiente, 11, 28049, Madrid, Spain

    Javier Ortega-García

  5. Departamento de Señales, Sistemas y Radiocomunicaciones ETSI Telecomunicación, Universidad Politécnica de Madrid , Av. Complutense 30, 28040, Madrid, Spain

    Ana M. Bernardos Barbolla

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Cilla, R., Patricio, M.A., Berlanga, A., Molina, J.M. (2011). Evaluating Manifold Learning Methods and Discriminative Sequence Classifiers in View-Invariant Action Recognition. In: Molina, J.M., Corredera, J.R.C., Pérez, M.F.C., Ortega-García, J., Barbolla, A.M.B. (eds) User-Centric Technologies and Applications. Advances in Intelligent and Soft Computing, vol 94. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19908-0_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-19908-0_2

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-19907-3

  • Online ISBN: 978-3-642-19908-0

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation