Skip to main content
SpringerLink
Log in

An Efficient Method for Extracting Key-Frames from 3D Human Joint Locations for Action Recognition

  • Conference paper
  • First Online:
Image Analysis and Recognition (ICIAR 2015)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 9164))

Included in the following conference series:

Abstract

Human Action Recognition is one of the intriguing research area of modern Artificial Intelligence and Computer Vision where different techniques are followed to distinguish various human actions. Accuracy of such methods mainly depend on how a sequence of action frames can be represented by a number of most distinguishable frames, otherwise called key frames. In this paper, we have introduced an efficient method to extract key frames by maximizing accumulation of motion between frames for recognizing human actions using the help of 3D skeletal joint locations. Our feature representation is the combination of histogram of joint 3D (HOJ3D) and static posture feature of 3D skeletal joint locations. Then we used Hidden Markov Model (HMM) for human action recognition from the extracted frame sequence.

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 EPUB and 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

References

  1. Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from a single depth image. In: Computer Vision And Pattern Recognition (CVPR) (2011)

    Google Scholar 

  2. Yang, X., Tian, Y.: Effective 3D action recognition using eigenjoints. Vis. Commun. Image Represent. 25(1), 2–11 (2014)

    Article  MathSciNet  Google Scholar 

  3. Xia, L., Chen, C.-C., Aggarwal, J.K.: View invariant human action recognition using histograms of 3D joints. In: CVPR Workshops, IEEE, pp. 20–27 (2012)

    Google Scholar 

  4. 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 

  5. Meng, H., Pears, N., Bailey, C.: A human action recognition system for embedded computer vision application. In: Proceedings of the CVPR (2007)

    Google Scholar 

  6. Davis, J.W., Tyagi, A.: Minimal-latency human action recognition using reliable-inference. Image Vis. Comput. 24(5), 455–473 (2006)

    Article  Google Scholar 

  7. Chen, D.-Y., Liao, H.-Y.M., Shih, S.-W.: Human action recognition using 2-D spatio-temporal templates. In: Proceedings of the ICME, pp. 667–670 (2007)

    Google Scholar 

  8. Kellokumpu, V., Pietikainen, M., Heikkila, J.: Human activity recognition using sequences of postures. In: Proceedings of the IAPR Conference on Machine Vision Applications, pp. 570–573 (2005)

    Google Scholar 

  9. Sminchisescu, C., Kanaujia, A., Li, Z., Metaxas, D.: Conditional models for contextual human motion recognition. In: Proceedings of the ICCV, vol. 2, pp. 808–815 (2005)

    Google Scholar 

  10. Zhang, J., Gong, S.: Action categoration with modified hidden conditional random field. Pattern Recogn. 43, 197–203 (2010)

    Article  MATH  Google Scholar 

  11. Li, W., Zhang, Z., Liu, Z.: Expandable data-driven graphical modeling of human actions based on salient postures. IEEE Trans. Circuits Syst. Video Technol. 18(11), 1499–1510 (2008)

    Article  Google Scholar 

  12. Aggarwal, J.K., Ryoo, M.S.: Human activity analysis: a review. ACM Comput. Surv. (CSUR) 43(3), Article 16, 43p. (2011)

    Google Scholar 

  13. Turaga, P., Chellapa, R., Subrahmanian, V.S., Udrea, O.: Machine recognition of human activities: a survey. Trans. Circ. Syst. Video Technol. 18(11), 1473–1488 (2008)

    Article  Google Scholar 

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

    Article  Google Scholar 

  15. Meng, H., Pears, N., Bailey, C.: A human action recognition system for embedded computer vision application. In: Computer Vision and Pattern Recognition (CVPR), vol. 2(1), p. 2122 (2007)

    Google Scholar 

  16. Davis, J.W., Tyagi, A.: Minimal-latency human action. Image Vis. Comput. (IVC) 24(5), 455–473 (2006)

    Article  Google Scholar 

  17. Kellokumpu, V., Pietikainen, M., Heikkila, J.: Human activity recognition using sequences of postures. In: International Association of Pattern Recognition (IAPR) (2005)

    Google Scholar 

  18. Thanh, T.T., FanChen, K.B.: Extraction of discriminative patterns from skeleton sequences for accurate action recognition. Fundamenta Informaticae XX, 15 (2012). doi:10.3233/FI-2012-0000. IOS Press

    Google Scholar 

  19. Huang, P., Hilton, A., Starck J.: Automatic 3D video summarization: key frame extraction from self similarity. In: 4th International Symposium on 3D Data Processing, Atlanta, GA, USA. pp. 71–78, June 2008

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Islamic University of Technology, Dhaka, Bangladesh

    Md. Hasanul Kabir, Ferdous Ahmed &  Abdullah-Al-Tariq

Authors
  1. Md. Hasanul Kabir
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ferdous Ahmed
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Abdullah-Al-Tariq
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ferdous Ahmed .

Editor information

Editors and Affiliations

  1. University of Waterloo, Waterloo, Ontario, Canada

    Mohamed Kamel

  2. University of Porto, Porto, Portugal

    Aurélio Campilho

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Kabir, M.H., Ahmed, F., Abdullah-Al-Tariq (2015). An Efficient Method for Extracting Key-Frames from 3D Human Joint Locations for Action Recognition. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2015. Lecture Notes in Computer Science(), vol 9164. Springer, Cham. https://doi.org/10.1007/978-3-319-20801-5_30

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-20801-5_30

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-20800-8

  • Online ISBN: 978-3-319-20801-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation