Abstract
In this paper, we present a novel simple and efficient method for segmentation by classification of motion capture data automatically and with high accuracy. Classification of motion capture data demands dealing with high dimensional search space due to the high dimensionality of the motion capture data. The main contribution of this paper is a method for reducing this search space using the divide and conquer principle in a form of a taxonomy-tree which means a multi-level segmentation by classification algorithm, where the highest level classifies motion capture data into dynamic and static segments and the lowest level uses features of single body-parts to recognize wide range of human movements. The first implementation of this algorithm has given very promising results and proved that it is fast enough to be integrated in real-time systems such as robotics and surveillance systems.
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
Notes
- 1.
This data are captured at Chemnitz University of Technology.
References
Barbic, J. Safonova, A. Pan, J.Y., Faloutsos, C. Hodgins, J.K., Pollard, N.S.: Segmenting motion capture data into distinct behaviours. In: Graphics Interface, pp. 185–194 (2004)
Kulic, D., Nakamura, Y.: Scaffolding on-line segmentation of full body human motion patterns. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, Acropolis Convention Center, France (2008)
Yun, S., Park, A., Jung, K.: Graph-based high level motion segmentation using normalized cuts. World Academy of Science Engineering and Technology 20 (2008)
Zhou, F. De la Torre, F., Hodgins, J.K.: Aligned cluster analysis for temporal segmentation of human motion. In: IEEE Conference on Automatic Face and Gestures Recognition (2008)
Lin, J.F., Kulic, D.: Segmentation human motion for automated rehabilitaion exercise analysis. In: 34th Annual International Conference of the IEEE EMBS (2012)
Gong, Dian, Medioni, Gérard, Zhu, Sikai, Zhao, Xuemei: Kernelized temporal cut for online temporal segmentation and recognition. In: Fitzgibbon, Andrew, Lazebnik, Svetlana, Perona, Pietro, Sato, Yoichi, Schmid, Cordelia (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 229–243. Springer, Heidelberg (2012)
Nakata, T.: Temporal segmentation and recognition of body motion data based on inter-limb correlation analysis. In: Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems San Diego, CA, Oct 29–Nov 2 (2007)
Müllerm, M., Röder, T.: Motion templates for automatic classification and retrieval of motion capture data. In: Eurographics/ACM SIGGRAPH Symposium on Computer Animation (2006)
Zhao, L., Sukthankar, G.: A semi-supervised method for segmenting multi-modal data. In: Proceedings of the International Symposium on Quality of Life Technology (2009)
Cho, K., Chen, X.: Classifying and Visualizing Motion Capture Sequences using Deep Neural Networks. arXiv preprint arXiv:1306.3874 (2013)
Lv, Fengjun, Nevatia, Ramakant: Recognition and segmentation of 3-D human action using HMM and multi-class AdaBoost. In: Leonardis, Aleš, Bischof, Horst, Pinz, Axel (eds.) ECCV 2006. LNCS, vol. 3954, pp. 359–372. Springer, Heidelberg (2006)
Li, C., Kulkarni, P.R., Prabhakaran, B.: Segmentation and recognition of motion capture data stream by classification. Multimedia Tools Appl. 35, 55–70 (2007)
Bruderlin, A., Williams, L.: Motion signal processing. In: Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques, pp. 97–104 (1995)
CMU Graphics Lab Motion Capture Database, Subject #86. http://mocap.cs.cmu.edu/search.php?subjectnumber=86. Accessed 24 March 2014
Acknowledgments
The data used in this work was obtained from motion capture.cs.cmu.edu.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Supplementary material 1 (AVI 40089 kb)
336837_1_En_10_MOESM2_ESM.avi
Supplementary material 2 (AVI 12119 kb)
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Salamah, S., Zhang, L., Brunnett, G. (2015). Hierarchical Method for Segmentation by Classification of Motion Capture Data. In: Brunnett, G., Coquillart, S., van Liere, R., Welch, G., Váša, L. (eds) Virtual Realities. Lecture Notes in Computer Science(), vol 8844. Springer, Cham. https://doi.org/10.1007/978-3-319-17043-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-17043-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-17042-8
Online ISBN: 978-3-319-17043-5
eBook Packages: Computer ScienceComputer Science (R0)