AN AUTOMATIC APPROACH FOR PARAMETER SELECTION IN SELF-ADAPTIVE TRACKING

Daniela Hall, Rémi Emonet, James L. Crowley

2006

Abstract

In this article we propose an automatic approach for parameter selection of a tracking system. We show that such a self-adaptive tracking system achieves better tracking performance than a system with manually tuned parameters. Our approach requires little supervision by a user which makes this approach ideally suited for commercial applications. The self-adaptive component makes the system less sensitive to changing environmental conditions. Components for tracking, auto-critical evaluation and automatic parameter regulation serve to detect performance drops that trigger the parameter regulation process. The self-adaptive components require a quality measure based on a statistical scene reference model. We propose an automatic approach for the generation of such a reference model and compare several learning approaches. The experiments show that the auto-regulation of parameters significantly enhances the performance of the tracking system.

References

1. Caporossi, A., Hall, D., Reignier, P., and Crowley, J. (2004). Robust visual tracking from dynamic control

Paper Citation

in Harvard Style

Hall D., Emonet R. and L. Crowley J. (2006). AN AUTOMATIC APPROACH FOR PARAMETER SELECTION IN SELF-ADAPTIVE TRACKING . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 20-26. DOI: 10.5220/0001372600200026

in Bibtex Style

@conference{visapp06,
author={Daniela Hall and Rémi Emonet and James L. Crowley},
title={AN AUTOMATIC APPROACH FOR PARAMETER SELECTION IN SELF-ADAPTIVE TRACKING},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={20-26},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001372600200026},
isbn={972-8865-40-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - AN AUTOMATIC APPROACH FOR PARAMETER SELECTION IN SELF-ADAPTIVE TRACKING
SN - 972-8865-40-6
AU - Hall D.
AU - Emonet R.
AU - L. Crowley J.
PY - 2006
SP - 20
EP - 26
DO - 10.5220/0001372600200026