A COMPREHENSIVE ANALYSIS OF HUMAN MOTION CAPTURE DATA FOR ACTION RECOGNITION

Valsamis Ntouskos, Panagiotis Papadakis, Fiora Pirri

Abstract

In this paper, we present an analysis of human motion that can assist the recognition of human actions irrespective of the selection of particular features. We begin with an analysis on the entire set of preclassified motions in order to derive the generic characteristics of articulated human motion and complement the analysis by a more detailed inter-class analysis. The statistical analysis concerns features that describe the significancecontribution of the human joints in performing an action. Furthermore, we adopt a hierarchical analysis on the human body itself in the study of different actions, by grouping joints that share common characteristics. We present our experiments on standard databases for human motion capture data as well as a new commercial dataset with additional classes of human motion and highlight certain interesting results.

References

  1. Barbic?, J., Safonova, A., Pan, J.-Y., Faloutsos, C., Hodgins, J., and Pollard, N. (2004). Segmenting motion capture data into distinct behaviors. In Proc. Graphics Interface 2004, pages 185-194.
  2. Cheong Took, C. and Mandic, D. P. (2011). Augmented second-order statistics of quaternion random signals. Signal Process., 91:214-224.
  3. CMU (2003). Carnegie-mellon mocap database. http://mocap.cs.cmu.edu/.
  4. Fod, A., Matari, M., and Jenkins, C. (2002). Automated derivation of primitives for movement classification. Autonomous Robots, 12:39-54.
  5. Ginzberg, P. and Walden, A. (2011). Testing for quaternion propriety. Signal Processing, IEEE Transactions on, 59(7):3025 -3034.
  6. Jenkins, C. and Mataric, M. (2003). Automated derivation of behavior vocabularies for autonomous humanoid motion. In AMAS, pages 225-232. ACM.
  7. Kovar, L. and Gleicher, M. (2004). Automated extraction and parameterization of motions in large data sets. In ACM SIGGRAPH 2004, pages 559-568.
  8. Markley, F. L., Yang, C., Crassidis, J. L., and Oshman, Y. (2007). Averaging quaternions. Guidance, Control, and Dynamics, 30(4):1193 - 1196.
  9. Microsoft, C. (2010). Kinect. http://www.xbox.com/enUS/kinect.
  10. Mihai, G. D. (1999). The visual analysis of human movement: A survey. Computer Vision and Image Understanding, 73(1):82 - 98.
  11. mocapdata.com (2011). Eyes, japan co. ltd. http://www.mocapdata.com/.
  12. Muller, M., Roder, T., Clausen, M., Eberhardt, B., Krüger, B., and Weber, A. (2007). Documentation mocap database hdm05. Technical Report CG-2007-2, Universität Bonn.
  13. Okan, A. (2006). Compression of motion capture databases. ACM Transactions on Graphics, 25:890-897.
  14. Poppe, R. (2010). A survey on vision-based human action recognition. Image and Vision Computing, 28(6):976 - 990.
  15. Pullen, K. and Bregler, C. (2002). Motion capture assisted animation: texturing and synthesis. In Proc. of the 29th annual conf. on Computer graphics and interactive techniques, pages 501-508. ACM.
  16. Thomas, M., Adrian, H., and Volker, K. (2006). A survey of advances in vision-based human motion capture and analysis. Computer Vision and Image Understanding, 104(2-3):90 - 126.
Download


Paper Citation


in Harvard Style

Ntouskos V., Papadakis P. and Pirri F. (2012). A COMPREHENSIVE ANALYSIS OF HUMAN MOTION CAPTURE DATA FOR ACTION RECOGNITION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 647-652. DOI: 10.5220/0003868806470652


in Bibtex Style

@conference{visapp12,
author={Valsamis Ntouskos and Panagiotis Papadakis and Fiora Pirri},
title={A COMPREHENSIVE ANALYSIS OF HUMAN MOTION CAPTURE DATA FOR ACTION RECOGNITION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={647-652},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003868806470652},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - A COMPREHENSIVE ANALYSIS OF HUMAN MOTION CAPTURE DATA FOR ACTION RECOGNITION
SN - 978-989-8565-03-7
AU - Ntouskos V.
AU - Papadakis P.
AU - Pirri F.
PY - 2012
SP - 647
EP - 652
DO - 10.5220/0003868806470652