Skip to main content

Classifying Bio-Inspired Model of Point-Light Human Motion Using Echo State Networks

Part of the Lecture Notes in Computer Science book series (LNTCS,volume 10613)


We introduce a feature extraction scheme from a biologically inspired model using receptive fields (RFs) to point-light human motion patterns to form an action descriptor. The Echo State Network (ESN) which also has a biological plausibility is chosen for classification. We demonstrate the efficiency and robustness of applying the proposed feature extraction technique with ESN by constraining the test data based on arbitrary untrained viewpoints, in combination with unseen subjects under the following conditions: (i) lower sub-sampling frame rates to simulate data sequence loss, (ii) remove key points to simulate occlusion, and (iii) include untrained movements such as drunkard’s walk.


  • Echo state network
  • Motion capture
  • Motion recognition
  • Biological motion perception
  • Bio-inspired model

This is a preview of subscription content, access via your institution.

Buying options

USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-319-68600-4_11
  • Chapter length: 8 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
USD   39.99
Price excludes VAT (USA)
  • ISBN: 978-3-319-68600-4
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   54.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.


  1. CMU Graphics Lab: CMU Motion Capture Database.

  2. Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015

    Google Scholar 

  3. Jaeger, H.: Long Short-Term Memory in Echo State Networks: Details of a Simulation Study. Technical Report, Jacobs University, Bremen, Germany, February 2012

    Google Scholar 

  4. Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless telecommunication. Science 304(5667), 78–80 (2004)

    CrossRef  Google Scholar 

  5. Johansson, G.: Visual perception of biological motion and a model for its analysis. Percept. Psychophys. 14(2), 201–211 (1973)

    CrossRef  Google Scholar 

  6. Junejo, I.N., Dexter, E., Laptev, I., Perez, P.: View-independent action recognition from temporal self-similarities. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 172–185 (2011)

    CrossRef  Google Scholar 

  7. Kale, G.V., Patil, V.H.: A study of vision based human motion recognition and analysis. IJACI 7(2), 75–92 (2016)

    Google Scholar 

  8. Livne, M., Sigal, L., Troje, N.F., Fleet, D.J.: Human attributes from 3D pose tracking. Comput. Vision Image Underst. (CVIU) (2012)

    Google Scholar 

  9. Miller, L.E., Saygin, A.P.: Individual differences in the perception of biological motion: Links to social cognition and motor imagery. Cognition 128(2), 140–148 (2013)

    CrossRef  Google Scholar 

  10. Pascanu, R., Jaeger, H.: A neurodynamical model for working memory. Neural Netw. 24(2), 199–207 (2011)

    CrossRef  Google Scholar 

  11. Rautaray, S.S., Agrawal, A.: Vision based hand gesture recognition for human computer interaction: a survey. Artif. Intell. Rev. 43(1), 71 (2015)

    CrossRef  Google Scholar 

  12. Tanisaro, P., Schöning, J., Kurzhals, K., Heidemann, G., Weiskopf, D.: Visual analytics for video applications. Inf. Technol. 57, 30–36 (2015)

    Google Scholar 

  13. Tanisaro, P., Heidemann, G.: Time series classification using time warping invariant echo state networks. In: 15th IEEE International Conference on Machine Learning and Applications (ICMLA) (2016)

    Google Scholar 

  14. Tanisaro, P., Mahner, F., Heidemann, G.: Quasi view-independent human motion recognition in subspaces. In: Proceedings of 9th International Conference on Machine Learning and Computing (ICMLC) (2017)

    Google Scholar 

  15. Troje, N.F., Sadr, J., Geyer, H., Nakayama, K.: Adaptation aftereffects in the perception of gender from biological motion. J. Vision 6(8), 7 (2006)

    CrossRef  Google Scholar 

  16. Zhu, W., Lan, C., Xing, J., Zeng, W., Li, Y., Shen, L., Xie, X.: Co-occurrence feature learning for skeleton based action recognition using regularized deep lstm networks. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 3697–3703 (2016)

    Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Pattreeya Tanisaro .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Tanisaro, P., Lehman, C., Sütfeld, L., Pipa, G., Heidemann, G. (2017). Classifying Bio-Inspired Model of Point-Light Human Motion Using Echo State Networks. In: Lintas, A., Rovetta, S., Verschure, P., Villa, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2017. ICANN 2017. Lecture Notes in Computer Science(), vol 10613. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-68599-1

  • Online ISBN: 978-3-319-68600-4

  • eBook Packages: Computer ScienceComputer Science (R0)