Abstract
Motion segmentation is one of the key techniques in the context of motion analysis and generation. The basic idea is to split motion capture data into continuous segments that can be used to generate new motion sequences. For most applications, this segmentation is done manually leading to inaccurate and inconsistent results. This makes it difficult to conceive general methods for subsequent reassembly.
This paper proposes an automatic segmentation of motion capture data that results in deterministic segmentation points. The method can be considered as an advanced zero crossing segmentation technique. As zero crossing performs poorly on weak motion, a threshold is defined detecting phases of week motion. We distinguish two states: One for the resting phase and one for phases of movement. Splitting this second phase again, the presented approach leads to a symbolic level allowing later steps to be carried out without the need of considering spatio-temporal dependencies.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Al-Zubi, S., Sommer, G.: Imitation learning and transfering of human movement and hand grabbing to adapt to environment changes. In: Reinhard Klette, B.R., Metaxas, D. (eds.) 13th Workshop on Human Motion - Understanding, Modeling, Capture and Animation. LNCS. Springer, Heidelberg (2006)
Bakker, P., Kuniyoshi, Y.: Robot see, robot do: An overview of robot imitation. In: Fogarty, T.C. (ed.) AISB-WS 1996. LNCS, vol. 1143, pp. 3–11. Springer, Heidelberg (1996)
Barbic, J., Safonova, A., Pan, J.-Y., Faloutsos, C., Hodgins, J.K., Pollard, N.S.: Segmenting motion capture data into distinct behaviors. In: Graphics Interface, pp. 185–194 (2004)
Bouchard, D.: Automated time series segmentation for human motion analysis. Technical report, Philadelphia: Center for Human Modeling and Simulation University of Pennsylvania (2006)
Gehrig, D., Kuehne, H., Woerner, A., Schultz, T.: Hmm-based human motion recognition with optical flow data. In: IEEE International Conference on Humanoid Robots (Humanoids 2009), Paris, France (2009)
Demirdjian, D., Ko, T., Darrell, T.: Constraining human body tracking. In: ICCV ’03: Proceedings of the Ninth IEEE International Conference on Computer Vision, Washington, DC, USA, p. 1071. IEEE Computer Society, Los Alamitos (2003)
Do, M., Gehrig, D., Azad, P., Pastor, P., Asfour, T., Warner, A., Dillmann, R., Schultz, T.: Transfer of human movements to humanoid robots (2008)
Fod, A., Matari, M.J., Jenkins, O.C.: Automated derivation of primitives for movement classification. In: Proc. of First IEEE-RAS International Conference on Humanoid Robots (2000)
Gehrig, D., Fischer, A., Kuehne, H., Stein, T., Woerner, A., Schwameder, H., Schultz, T.: Online recognition of daily-life movements (2008)
Gehrig, D., Kuehne, H., Woerner, A., Schultz, T.: Hmm-based human motion recognition with optical flow data. In: 2009 9th IEEE-RAS International Conference on Humanoid Robots (2009)
Guerra-Filho, G.: The morphology of human action: Finding essential actuators, motiom patterns, and their coordination. International Journal on Humanoid Robotics (2009)
Guerra-Filho, G., Aloimonos, Y.: A sensory-motor language for human activity understanding. In: 2006 6th IEEE-RAS International Conference on Humanoid Robots, pp. 69–75 (2006)
Kahol, K., Tripathi, P., Panchanathan, S.: Automated gesture segmentation from dance sequences. In: Proceedings of Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 883–888 (2004)
Klette, R., Tee, C.: Understanding human motion: A historic review, p. 1 (2008)
Kulic, D., Lee, D., Ott, C., Nakamura, Y.: Incremental learning of full body motion primitives for humanoid robots. In: 2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids, pp. 326–332 (2008)
Kulic, D., Nakamura, Y.: Comparative study of representations for segmentation of whole body human motion data. In: IROS, pp. 4300–4305 (2009)
Musto, A.: A fuzzy-based, qualitative representation of movement. Technical report (2008)
Nakazawa, A., Nakaoka, S., Ikeuchi, K., Yokoi, K.: Imitating human dance motions through motion structure analysis. In: Proc. of International Conference on Intelligent Robots and Systems, pp. 2539–2544 (2002)
Rizzolatti, G., Craighero, L.: The mirror-neuron system. Annu. Rev. Neuroscience (2004)
Simonidis, C., Gaertner, S., Do, M.: Spezifikationen zu den ganzkoerpermenschmodellen im sfb 588. Technical report, Universitaets Verlag Karlsruhe (2009)
Pomplun, M., Matarić, M.: Evaluation metrics and results of human arm movement imitation. In: Proceedings of the 1st IEEE-RAS International Conference on Humanoid Robotics (2000)
Koenig, N.: Behavior-based segmentation of demonstrated task (2006)
Ilg, W., Bakir, G., Mezger, J., Giese, M.: On the representation, learning and transfer of spatio-temporal movement characteristics (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schulz, S., Woerner, A. (2010). Automatic Motion Segmentation for Human Motion Synthesis. In: Perales, F.J., Fisher, R.B. (eds) Articulated Motion and Deformable Objects. AMDO 2010. Lecture Notes in Computer Science, vol 6169. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-14061-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-14061-7_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-14060-0
Online ISBN: 978-3-642-14061-7
eBook Packages: Computer ScienceComputer Science (R0)