August 2010
Volume 10, Issue 7
Free
Vision Sciences Society Annual Meeting Abstract  |   August 2010
Segmentation of action streams: comparison between human and statistically optimal performance
Author Affiliations
  • Dominik Endres
    Section for Computational Sensomotorics, Dept. for Cognitive Neurology, Hertie Institute for Clinical Brain Research & Center for Integrative Neurocience, University Clinic Tuebingen, Germany
  • Cornelia Beck
    Institute for Neural Information Processing, Faculty of Engineering and Computer Sciences, University of Ulm, Germany
  • Jan Bouecke
    Institute for Neural Information Processing, Faculty of Engineering and Computer Sciences, University of Ulm, Germany
  • Lars Omlor
    Section for Computational Sensomotorics, Dept. for Cognitive Neurology, Hertie Institute for Clinical Brain Research & Center for Integrative Neurocience, University Clinic Tuebingen, Germany
  • Heiko Neumann
    Institute for Neural Information Processing, Faculty of Engineering and Computer Sciences, University of Ulm, Germany
  • Martin Giese
    Section for Computational Sensomotorics, Dept. for Cognitive Neurology, Hertie Institute for Clinical Brain Research & Center for Integrative Neurocience, University Clinic Tuebingen, Germany
Journal of Vision August 2010, Vol.10, 807. doi:10.1167/10.7.807
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Dominik Endres, Cornelia Beck, Jan Bouecke, Lars Omlor, Heiko Neumann, Martin Giese; Segmentation of action streams: comparison between human and statistically optimal performance. Journal of Vision 2010;10(7):807. doi: 10.1167/10.7.807.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Natural body movements arise in form of temporal sequences of individual actions. In order to realize a visual analysis of these actions, the visual system must accomplish a temporal segmentation of such action sequences. Previous work has studied in detail the segmentation of sequences of piecewise linear movements in the two-dimensional plane [1,2] In our study, we tried to compare statistical approaches for segmentation of human full-body movement with human responses. Video sequences were generated by synthesized sequences of natural actions based on motion capture, using appropriate methods for motion blending. Human segmentation was assessed by an interactive adjustment paradigm, where participants had to indicate segmentation points by selection of the relevant frames. This psychophysical data was compared against different segmentation algorithms, which were based: (1) on the available 3D joint trajectories that were used for the synthesis of the motion stimuli; (2) on the two-dimensional optic flow computed from the videos. This computation exploited a physiologically-inspired neural algorithm for optic flow estimation [3]. Simple segmentation methods, e.g. based on discontinuities in path direction or speed, were compared with an optimal Bayesian action segmentation approach from machine learning. This method is based on a generative classifier (naive Bayesian or HMM). Transitions between classes (types of actions) were modeled by resetting the class priors at the change points. Change point configurations were modeled by Bayesian binning [4]. Applying optimization within a Bayesian framework, number and the length of individual action segments were determined automatically. Performance of these different algorithmic methods was compared with human performance.

[1] Shipley et al., JOV, 4(8), 2004.

[2] Agam & Sekuler JOV, 8(1), 2008.

[3] Bayerl & Neumann, IEEE PAMI 29(2), 2007.

[4] Endres et al., NIPS 20, 2008.

Endres, D. Beck, C. Bouecke, J. Omlor, L. Neumann, H. Giese, M. (2010). Segmentation of action streams: comparison between human and statistically optimal performance [Abstract]. Journal of Vision, 10(7):807, 807a, http://www.journalofvision.org/content/10/7/807, doi:10.1167/10.7.807. [CrossRef]
Footnotes
 Funded by the EC FP7 project SEARISE, DFG, and Herman Lilly Schilling Foundation.
×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×