Posture Recognition Based on Slow Feature Analysis

Chapter

Abstract

Basic postures such as sit, stand and lie are ubiquitous in human interaction. In order to build robots that aid and support humans in their daily life, we need to understand how posture categories can be learned and recognized. This paper presents an unsupervised learning approach to posture recognition for a biped humanoid robot. The approach is based on Slow Feature Analysis (SFA), a biologically inspired algorithm for extracting slowly changing signals from signals varying on a fast time scale. Two experiments are carried out: First, we consider the problem of recognizing static postures in a multimodal sensory stream which consists of visual and proprioceptive stimuli. Secondly, we show how to extract a low-dimensional representation of the sensory state space which is suitable for posture recognition in a more complex setting. We point out that the beneficial performance of SFA in this task can be related to the fact that SFA computes manifolds which are used in robotics to model invariants in motion and behavior. Based on this insight, we also propose a method for using SFA components for guided exploration of the state space.

Key words

posture recognition Slow Feature Analysis unsupervised learning dimensionality reduction humanoid robotics 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Berkes P (2006) Temporal slowness as an unsupervised learning principle. PhD thesis, Humboldt-Universitat zu BerlinGoogle Scholar
  2. Berkes P, Wiskott L (2002) Applying Slow Feature Analysis to Image SequencesGoogle Scholar
  3. Yields a Rich Repertoire of Complex Cell Properties. In: Dorronsoro JR (ed)Google Scholar
  4. Proc. Intl. Conf. on Artificial Neural Networks - ICANN’02, Springer, Lecture Notes in Computer Science, pp 81–86Google Scholar
  5. Berkes P, Wiskott L (2006) On the analysis and interpretation of inhomogeneous quadratic forms as receptive fields. Neural Computation 18(8):1868–1895MathSciNetCrossRefMATHGoogle Scholar
  6. Franzius M, Sprekeler H, Wiskott L (2007) Slowness and sparseness lead to place, head-direction, and spatial-view cells. PLoS Computational Biology 3(8):e166MathSciNetCrossRefGoogle Scholar
  7. Hild M, Siedel T, Benckendorff C, Thiele C, Spranger M (2012) Myon, a NewGoogle Scholar
  8. Humanoid. In: Steels L, Hild M (eds) Language Grounding in Robots, Springer, New YorkGoogle Scholar
  9. Hofer S, Hild M (2010) Using Slow Feature Analysis to Improve the Reactivity of a Humanoid Robot’s Sensorimotor Gait Pattern. In: International Conference on Neural Computation (ICNC 2010), Valencia, Spain, pp 212 – 219Google Scholar
  10. Li S, de Vel O, Coomans D (1995) Comparative performance analysis of non-linear dimensionality reduction methods. Tech. rep., James Cook University, NorthGoogle Scholar
  11. Moeslund TB, Hilton A, Kruger V (2006) A survey of advances in vision-based human motion capture and analysis. Computer Vision and Image Understanding 104(2-3):90–126, DOI 10.1016/j.cviu.2006.08.002CrossRefGoogle Scholar
  12. Mukundan R, Ramakrishnan K (1998) Moment functions in image analysis: theory and applications. World Scientific PublishingGoogle Scholar
  13. Pearson K (1901) On lines and planes of closest fit to systems of points in space. Philosophical Magazine 2:559–572Google Scholar
  14. Plagemann C, Ganapathi V, Koller D, Thrun S (2010) Real-time identification and localization of body parts from depth images. In: 2010 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp 3108–3113, DOI 10.1109/ROBOT.2010.5509559Google Scholar
  15. Ronald P (2007) Vision-based human motion analysis: An overview. Computer Vision and Image Understanding 108(1-2):4–18, DOI 10.1016/j.cviu.2006.10.016, URL http://www.sciencedirect.com/science/article/pii/S1077314206002293
  16. Rousseeuw P (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20(1):53–65CrossRefMATHGoogle Scholar
  17. Roweis S, Saul L (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326CrossRefGoogle Scholar
  18. Selig J (2005) Geometric Fundamentals of Robotics. Springer, New YorkMATHGoogle Scholar
  19. Spranger M, Loetzsch M (2009) The semantics of sit, stand, and lie embodied inGoogle Scholar
  20. robots. In: Taatgen NA, van Rijn H (eds) Proceedings of the 31th Annual Conference of the Cognitive Science Society (Cogsci09), Cognitive Science Society, Austin, TX, pp 2546–2552Google Scholar
  21. Spranger M, Hofer S, Hild M (2009) Biologically inspired posture recognition and posture change detection for humanoid robots. In: Proc. IEEE International Conference on Robotics and Biomimetics (ROBIO), Guilin, China, pp 562–567Google Scholar
  22. Steels L, SprangerM(2008) The robot in the mirror. Connection Science 20(4):337– 358Google Scholar
  23. Wiskott L (1998) Learning Invariance Manifolds. In: Proc. of the 5th Joint Symp. on Neural Computation, May 16, San Diego, CA, Univ. of California, San Diego, CA, vol 8, pp 196–203Google Scholar
  24. Wiskott L (2003a) Estimating Driving Forces of Nonstationary Time Series with Slow Feature AnalysisGoogle Scholar
  25. Wiskott L (2003b) Slow Feature Analysis: A Theoretical Analysis of Optimal Free Responses. Neural Computation 15(9):2147–2177CrossRefMATHGoogle Scholar
  26. Wiskott L, Sejnowski T (2002) Slow Feature Analysis: Unsupervised Learning of Invariances. Neural Computation 14(4):715–770CrossRefMATHGoogle Scholar
  27. Zito T, Wilbert N, Wiskott L, Berkes P (2009) Modular toolkit for Data Processing (MDP): a Python data processing frame workGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Sebastian Höfer
    • 1
  • Michael Spranger
    • 2
    • 3
  • Manfred Hild
    • 3
    • 4
  1. 1.Robotics and Biology LaboratoryTechnische Universität BerlinBerlinGermany
  2. 2.Systems Technology LaboratorySony CorporationTokyoJapan
  3. 3.Sony Computer Science LaboratoryParisFrance
  4. 4.Neurorobotics Research LaboratoryHumboldt-Universität zu BerlinBerlinGermany

Personalised recommendations