Dynamical Motion Capture System Involving via Neural Networks

  • Eva Volná
  • Robert Jarušek
  • Martin Kotyrba
  • Daniel Rucký
Conference paper
Part of the Springer Proceedings in Complexity book series (SPCOM)

Abstract

The aim of this article is to outline possibilities of sound and its physical properties during shooting of moving objects. Attention was devoted to the specific location of a fixed point in the space and time. We proposed appropriate topology of the system that depends on the required accuracy, acoustic properties and selected sound technologies. Developed software, which processes a detected sound signal, is based on artificial neural networks. The neural network identifies a distance between an active transmitter and a receiver on the basis of sound pulses transmit-ted from transmitters in the defined domain. Consequently, another neural net-work uses obtained distances between transmitters and a receiver as its inputs to determine an actual position of the receiver in space. Developed software is implemented in C language.

Keywords

Neural Network Hide Layer Main Sequence Motion Capture System Sound Pulse 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. Everest FA (2000) Master handbook of acoustics, 4th edn. New York: McGarff-Hill TAB Electronics, 592 s. ISBN: 0071360972Google Scholar
  2. Fausett L (1994) Fundamentals of neural network. New Jersey: Prentice Hall. ISBN: 0-13-334186-0Google Scholar
  3. Huber DM, Runstein RE (2005) Modern recording techniques, 6th edn. Oxford: Focal Press, 672 s. ISBN: 0240806255Google Scholar
  4. Jarušek R (2009) Neural network in motion capture technology with sound waves using (in Czech). Bachelor thesis, University of OstravaGoogle Scholar
  5. Sejdić E, Djurović I, Jiang J, Stanković LJ (2009) Time-frequency based feature extraction and classification: considering energy concentration as a feature using stockwell transform and related approaches. VDM Verlag, Saarbrücken. ISBN 978-953-7619-24-4Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2014

Authors and Affiliations

  • Eva Volná
    • 1
  • Robert Jarušek
    • 1
  • Martin Kotyrba
    • 1
  • Daniel Rucký
    • 1
  1. 1.University of OstravaOstravaCzech Republic

Personalised recommendations