Abstract
In this chapter we present a method that combines neural networks and the inverse kinematics to allow a considerable reduction of the number of motion capture data packets sent over network.A subset of inverse kinematics,the SHAKE algorithm, is used to configure an articulated skeleton model.The role of the neural network is to learn the sensor's behaviour during training with all sensors attached to the user and to predict the locations of OFF sensors by taking ON sensor(s) as input. ln this way, the number of sensors can be reduced to as few as one.
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
J. Zhao and N.I. Badler, Real time inverse Kinematics with joint limits and spatial constraints, Technical Report MS-CIS-89-09, GRAPHICS LAB 27, January 1989.
R. Boulic, R. Mas and D. Thalmann, Inverse Kinetics for center of mass position control and posture optimization. Proceedings of European Workshop on Combined Real and Senthic Image Processing for Broadcast and Video Production, Hamburg, November 1994.
W. Tang, M. Cavazza, D. Mountain and R. Earnshaw, A constrained inverse technique for real-time motion capture animation. Visual Computer, 15: 413–425,1999.
J. Ryckaert, G. Ciccotti and H.J. Berendsen, Numerical integration of the cartesian equations of motion of a system with constraints: molecular dynamics of n-alkanes. Journal of Computational Physics, 23: 327–341, 1977.
T. Kastenmeier and F.J. Vesely, Numerical robot kinematics based on stochastic and molecular simulation methods. Robotica, 14: 329–337, 1996.
Z.R. Novakovic and B. Nemec, A solution to the inverse kinematics problem using the sliding mode, IEEE Transactions on Robotics Automation, 6(2): 247–252, 1990.
R.P. Lippmann, Introduction to computing with neural nets. Speech and Signal Processing Magazine, 4(2): 4–22, 1987.
H. Amin, K.M. Curtis and B.R. Hayes-Gill, Piecewise linear approximation applied to nonlinear function of a neural network. IEE Proc. Circuits Devices and Systems, 144(6): 313–317, 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag London
About this chapter
Cite this chapter
Amin, H., Reeve, C.M., Earnshaw, R. (2001). Enhanced Avatar Control Using Neural Networks. In: Earnshaw, R., Vince, J. (eds) Digital Content Creation. Springer, London. https://doi.org/10.1007/978-1-4471-0293-9_17
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0293-9_17
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1079-8
Online ISBN: 978-1-4471-0293-9
eBook Packages: Springer Book Archive