Skip to main content
SpringerLink
Log in

Directional Stationary Wavelet-Based Representation for Human Action Classification

  • Conference paper
Advanced Machine Learning Technologies and Applications (AMLTA 2014)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 488))

Abstract

This paper proposes a directional wavelet-based representation of natural human actions in realistic videos. This task is very important for human action recognition, which has become one of the most important fields in computer vision. Its importance comes from the large number of applications that employ human action classification and recognition. The proposed method utilizes the 3D Stationary Wavelet Analysis to encode the directional spatio-temporal characteristics of the motion available in video sequences. It was tested using the Weizmann dataset, and produced promising preliminary results (92.47 % classification accuracy) when compared to existing state–of–the–art methods.

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

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. Kim, I.S., Choi, H.S., Yi, K.M., Choi, J.Y., Kong, S.G.: Intelligent Visual Surveillance: a survey. Int. J. Control, Automation, and Systems 8, 926–939 (2010)

    Article  Google Scholar 

  2. Pantic, M., Nijholt, A., Pentland, A., Huanag, T.S.: Human- Centered Intelligent Human-Computer Interaction (HCI2): How far are we from attaining it? Int. J. Autonomous and Adaptive Communications Systems 1(2), 168–187 (2008)

    Article  Google Scholar 

  3. Moeslund, T.B., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. Comput. Vis. Image Und. 104, 90–126 (2006)

    Article  Google Scholar 

  4. Thi, T.H., Cheng, L., Zhang, J., Wang, L., Satoh, S.: Structured learning of local features for human action classification and localization. Image Vision Comput. 30, 1–14 (2012)

    Article  Google Scholar 

  5. Poppe, R.: A survey on vision-based human action recognition. Image Vision Comput. 28, 976–990 (2010)

    Article  Google Scholar 

  6. Cristani, M., Raghavendra, R., Del Bue, A., Murino, V.: Human Behavior Analysis in Video Surveillance: Social Signal Processing Perspective. Neurocomputing 100, 86–97 (2013)

    Article  Google Scholar 

  7. Weinland, D., Ranford, R., Boyer, E.: A survey of vision-based methods for action representation, segmentation and recognition. Comput. Vis. Image Und. 115, 224–241 (2011)

    Article  Google Scholar 

  8. Pantic, M., Nijholt, A., Pentland, A., Huanag, T.: Machine Understanding of Human Behavior. In: ACM Int. Conf. Multimodal Interface (2006)

    Google Scholar 

  9. Turaga, P., Chellappa, R., Subrahamanian, V., Udrea, O.: Machine Recognition of Human Activities: A Survey. IEEE T. Circ. Syst. Vid. 18(11), 1473–1487 (2008)

    Article  Google Scholar 

  10. Davis, J.W.: Representing and Recognizing Human Motion: From Motion Templates to Movement Categories. In: Digital Human Modeling Workshop, IROS 2001 (2001)

    Google Scholar 

  11. Babu, R.V., Ramakrishnan, K.R.: Recognition of human actions using motion history information extrcted from the compressed video. Image Vision Comput. 22, 597–607 (2004)

    Article  Google Scholar 

  12. Ahad, M., Tan, J., Kim, H., Ishikawa, S.: Motion history image: its variants and applications. Mach. Vision Appl. 23, 255–281 (2012)

    Article  Google Scholar 

  13. Al-Berry, M.N., Salem, M.A.-M., Hussein, A.S., Tolba, M.F.: Spatio-Temporal Motion Detection for Intelligent Surveillance Applications. Int. J. Computational Methods 11(1), 1 (2014)

    Google Scholar 

  14. Hu, M.-K.: Visual Pattern Recognition by Moment Invariants. IEEE T. Inform. Theory 8(2), 179–187 (1962)

    Article  MATH  Google Scholar 

  15. Aggrawal, J., Cai, Q.: Human Motion Analysis: A Review. Comput. Vis. Image Und. 73(3), 428–440 (1999)

    Article  Google Scholar 

  16. Vishwakarma, S., Agrawal, A.: A survey on activity recognition and behavior understanding in video surveillance. The Visual Computer 29(10), 983–1009 (2013)

    Article  Google Scholar 

  17. Yan, X., Luo, Y.: Recognizing human actions using a new descriptor based on spatial–temporal interest points and weighted-output classifier. Neurocomputing 87, 51–61 (2012)

    Article  Google Scholar 

  18. Chen, M.Y.: MoSIFT: Resognizing Human Actions in Surveillance Videos, School of Cegie Mellon Universityomputer Science at Research Showcase . Carnegie Mellon University (2009)

    Google Scholar 

  19. Bregonzio, M., Xiang, T., Gong, S.: Fusing appearance and distribution information of interest points for action recognition. Pattern Recogn. 45, 1220–1234 (2012)

    Article  Google Scholar 

  20. Rapantzikos, K., Tsapatsoulis, N., Avrithis, Y., Kollias, S.: Spatiotemporal saliency for event detection and representation in the 3D Wavelet Domain: Potential in human action recognition. Signal Processing: Image Communication 24, 557–571 (2009)

    Google Scholar 

  21. Rapantzikos, K., Avrithis, Y., Kollias, S.: Spatiotemporal saliency for event detec-tion and representation in the 3D Wavelet Domain: Potential in human action recognition. In: 6th ACM International Conference on Image and Video Retrieval, pp. 294–301 (2007)

    Google Scholar 

  22. Sharma, A., Kumar, D.K., Kumar, S., McLachlan, N.: Wavelet Directional Histograms for Classification of Human Gestures Represented by Spatio-Temporal Templates. In: 10th International Multimedia Modeling Conference MMM 2004, pp. 57–63 (2004)

    Google Scholar 

  23. Davies, J., Bobick, A.F.: The representation and recognition of human movements using temporal templates. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 928–934 (1997)

    Google Scholar 

  24. Shao, L., Ji, L., Liu, Y., Zhang, J.: Human action segmentation and recognition via motion and shape analysis. Pattern Recogn. Lett. 33, 438–445 (2012)

    Article  Google Scholar 

  25. Weinland, D., Ronfard, R., Boyer, E.: Free Viewpoint Action Recognition using Motion History Volumes. Comput. Vis. Image Und. 104(2), 249–257 (2006)

    Article  Google Scholar 

  26. Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Printice Hall (2008)

    Google Scholar 

  27. Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as Space-time Shapes. In: 10th International Conference on Computer Vision, pp. 1395–1402 (2005)

    Google Scholar 

  28. Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition. In: 15th ACM International Conference on Multimedia, pp. 357–360 (2007)

    Google Scholar 

  29. Ballan, L., Bertini, M., Del Bimbo, A., Seidenari, L., Serra, G.: Recognizing Human Actions by fusing Spatio-temporal Appearance and Motion Descriptors. In: 16th IEEE International Conference on Image Processing, ICIP 2009, pp. 3569–3572 (2009)

    Google Scholar 

  30. Kong, Y., Zhang, X., Hu, W., Jia, Y.: Adaptive learning codebook for action recog-nition. Pattern Recogn. Lett. 32, 1178–1186 (2011)

    Article  Google Scholar 

  31. Schindler, K., Gool, L.V.: Action snippets: how many frames does human action recognition require. In: IEEE Conf. Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8 (2008)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Scientific Computing Department, Faculty of Computer and Information Sciences, Ain Shams University, Egypt

    M. N. Al-Berry, M. A. -M. Salem, Hala M. Ebeid & Mohamed Fahmy Tolba

  2. Faculty of Computer Studies, Arab Open University, Kuwait

    A. S. Hussein

Authors
  1. M. N. Al-Berry
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. A. -M. Salem
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hala M. Ebeid
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. A. S. Hussein
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mohamed Fahmy Tolba
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Cairo University, Egypt

    Aboul Ella Hassanien

  2. Ain Shams University, Cairo, Egypt

    Mohamed F. Tolba

  3. Benha University, Benha, Egypt

    Ahmad Taher Azar

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this paper

Cite this paper

Al-Berry, M.N., Salem, M.A.M., Ebeid, H.M., Hussein, A.S., Tolba, M.F. (2014). Directional Stationary Wavelet-Based Representation for Human Action Classification. In: Hassanien, A.E., Tolba, M.F., Taher Azar, A. (eds) Advanced Machine Learning Technologies and Applications. AMLTA 2014. Communications in Computer and Information Science, vol 488. Springer, Cham. https://doi.org/10.1007/978-3-319-13461-1_30

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-13461-1_30

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-13460-4

  • Online ISBN: 978-3-319-13461-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation