Abstract
The use of adaptive Gaussian mixtures to model the colour distributions of objects is described. These models are used to perform robust, real-time tracking under varying illumination, viewing geometry and camera parameters. Observed log-likelihood measurements were used to perform selective adaptation.
Supported by an EPSRC/BBC CASE Studentship and EPSRC Grant GR/K44657.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
C. Bishop. Neural Networks for Pattern Recognition. Oxford University Press, 1995.
D. A. Forsyth. Colour Constancy and its Applications in Machine Vision. PhD thesis, University of Oxford, 1988.
R. Kjeldsen and J. Kender. Finding skin in color images. In 2nd Int. Conf. on Automatic Face and Gesture Recognition, 1996.
S. McKenna, S. Gong, and Y. Raja. Face recognition in dynamic scenes. In BMVC, 1997.
Y. Raja, S. McKenna, and S. Gong. Segmentation and tracking using colour mixture models. In Asian Conference on Computer Vision, 1998.
R. A. Redner and H. F. Walker. Mixture densities, maximum likelihood and the EM algorithm. SIAM Review, 26(2):195–239, 1984.
M. J. Swain and D. H. Ballard. Colour indexing. IJCV, pages 11–32, 1991.
H. G. C. Traven. A neural network approach to statistical pattern classification by “semiparametric” estimation of probability density functions. IEEE Trans. Neural Networks, 2(3):366–378, 1991. *** DIRECT SUPPORT *** A0008188 00021
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
McKenna, S.J., Raja, Y., Gong, S. (1997). Object tracking using adaptive colour mixture models. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1351. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63930-6_174
Download citation
DOI: https://doi.org/10.1007/3-540-63930-6_174
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63930-5
Online ISBN: 978-3-540-69669-8
eBook Packages: Springer Book Archive