Advertisement

Discrimination of Locomotion Direction at Different Speeds: A Comparison between Macaque Monkeys and Algorithms

  • Fabian Nater
  • Joris Vangeneugden
  • Helmut Grabner
  • Luc Van Gool
  • Rufin Vogels
Part of the Studies in Computational Intelligence book series (SCI, volume 384)

Abstract

Models for visual motion perception exist since some time in neurophysiology as well as computer vision. In this paper, we present a comparison between a behavioral study performed with macaque monkeys and the output of a computational model. The tasks include the discrimination between left and right walking directions and forward vs. backward walking. The goal is to measure generalization performance over different walking and running speeds. We show in which cases the results match, and discuss and interpret differences.

Keywords

Macaque Monkey Biological Motion Response Target Monkey Response Human Action Recognition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Giese, M.A., Poggio, T.: Neural mechanisms for the recognition of biological movements. Nature Reviews, Neuroscience 4, 179–192 (2003)CrossRefGoogle Scholar
  2. 2.
    Schindler, K., van Gool, L.: Action snippets: How many frames does human action recognition require? In: Proc. CVPR (2008)Google Scholar
  3. 3.
    Lange, J., Lappe, M.: A model of biological motion perception from con gural form cues. Journal of Neurosciences 26, 2894–2906 (2006)Google Scholar
  4. 4.
    Vangeneugden, J., Vancleef, K., Jaeggli, T., Gool, L.V., Vogels, R.: Discrimination of locomotion direction in impoverished displays of walkers by macaque monkeys. Journal of Vision 10, 1–19 (2010)CrossRefGoogle Scholar
  5. 5.
    Nater, F., Grabner, H., Gool, L.V.: Exploiting simple hierarchies for unsupervised human behavior analysis. In: Proc. CVPR (2010)Google Scholar
  6. 6.
    Vangeneugden, J., Pollick, F., Vogels, R.: Functional di erentiation of macaque visual temporal cortical neurons using a parametric action space. Cerebral Cortex 19, 593–611 (2009)CrossRefGoogle Scholar
  7. 7.
    Lv, F., Nevatia, R.: Single view human action recognition using key pose matching and viterbi path searching. In: Proc. CVPR (2007)Google Scholar
  8. 8.
    Boiman, O., Irani, M.: Detecting irregularities in images and in video. In: Proc. ICCV (2005)Google Scholar
  9. 9.
    Fidler, S., Berginc, G., Leonardis, A.: Hierarchical statistical learning of generic parts of object structure. In: Proc. CVPR (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Fabian Nater
    • 1
  • Joris Vangeneugden
    • 2
  • Helmut Grabner
    • 1
  • Luc Van Gool
    • 1
    • 3
  • Rufin Vogels
    • 2
  1. 1.Computer Vision LaboratoryETH ZurichSwitzerland
  2. 2.Laboratorium voor Neuro- en PsychofysiologieK.U. LeuvenBelgium
  3. 3.ESAT - PSI / IBBTK.U. LeuvenBelgium

Personalised recommendations