Abstract
An important issue in tracking is how to incorporate an appropriate degree of adaptivity into the observation model. Without any adaptivity, tracking fails when object properties change, for example when illumination changes affect surface colour. Conversely, if an observation model adapts too readily then, during some transient failure of tracking, it is liable to adapt erroneously to some part of the background. The approach proposed here is to adapt selectively, allowing adaptation only during periods when two particular conditions are met: that the object should be both present and in motion. The proposed mechanism for adaptivity is tested here with a foreground colour and motion model. The experimental setting itself is novel in that it uses combined colour and motion observations from a fixed filter bank, with motion used also for initialisation via a Monte Carlo proposal distribution. Adaptation is performed using a stochastic EM algorithm, during periods that meet the conditions above. Tests verify the value of such adaptivity, in that immunity to distraction from clutter of similar colour to the object is considerably enhanced.
Chapter PDF
Similar content being viewed by others
Keywords
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
K.J. Astrom. Introduction to Stochastic Control Theory. Academic Press, 1970.
A. Blake, R. Curwen, and A. Zisserman. A framework for spatio-temporal control in the tracking of visual contours. Int. J. Computer Vision, 11(2):127–145, October 1993.
D. Comaniciu, V. Ramesh, and P. Meer. Real-time tracking of non-rigid objects using mean shift. In Proc. Conf. Comp. Vision Pattern Rec., pages II: 142–149, 2000.
A Doucet and D Crisan. A survey of convergence results on particle filtering for practitioners. IEEE Trans. Signal Processing, 2001. To Appear.
A. Doucet, J. F. G. de Freitas, and N. J. Gordon, editors. Sequential Monte Carlo Methods in Practice. Springer-Verlag, New York, 2001.
C. Harris. Tracking with rigid models. In A. Blake and A.L. Yuille, editors, Active Vision, pages 59–74. MIT, 1992.
M. Isard and A. Blake. CONDENSATION-conditional density propagation for visual tracking. Int. J. Computer Vision, 28(1):5–28, 1998.
M. Isard and J. MacCormick. BraMBLe: A Bayesian multiple-blob tracker. In Proc. Int. Conf. Computer Vision, pages II: 34–41, 2001.
H.T. Nguyen, M. Worring, and R. van den Boomgaard. Occlusion robust adaptive template tracking. In ICCV, pages I: 678–683, 2001.
C. P. Robert and G. Casella. Monte Carlo Statistical Methods. Springer-Verlag, New York, 1999.
J. Sullivan, A. Blake, M. Isard, and J. MacCormick. Bayesian object localisation in images. IJCV, 44(2):111–135, September 2001.
K. Toyama and A. Blake. Probabilistic tracking in a metric space. In Proc. Int. Conf. Computer Vision, pages II: 50–57, 2001.
Y. Wu and T. Huang. Color tracking by transductive learning. In CVPR, pages I: 133–138, 2000.
Y. Wu and T.S. Huang. A co-inference approach to robust visual tracking. In Proc. Int. Conf. Computer Vision, pages II: 26–33, 2001.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vermaak, J., Pérez, P., Gangnet, M., Blake, A. (2002). Towards Improved Observation Models for Visual Tracking: Selective Adaptation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds) Computer Vision — ECCV 2002. ECCV 2002. Lecture Notes in Computer Science, vol 2350. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-47969-4_43
Download citation
DOI: https://doi.org/10.1007/3-540-47969-4_43
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43745-1
Online ISBN: 978-3-540-47969-7
eBook Packages: Springer Book Archive