Abstract
Visual sensing systems are one of the most important information sources for autonomous mobile robots. By using temporal information, the object detection can be stabilized over time. In this paper we show, that a tight coupling between the visual system and such a tracking instance allows to integrate a lot more different information sources than it would be possible with two separate modules. This linkage between classification and temporal integration allows to stabilize and accelerate the detection task at the same time as shown in detail in the results section.
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
Ulrich Kaufmann, Gerd Mayer, Gerhard K. Kraetzschmar, and Günther Palm. Visual robot detection in robocup using neural networks. In RoboCup 2004: Robot Soccer World Cup VIII, Lecture Notes in Arti_cial Intelligence, pages 262–273, Berlin, Heidelberg, Germany, 2004. Springer.
Gerd Mayer, Ulrich Kaufmann, Gerhard Kraetzschmar, and Günther Palm. Neural robot detection in robocup. In Günther Palm and Stefan Wermter, editors, 27th German Conference on Arti_cial Intelligence (KI2004), NeuroBotics Workshop, pages 22–31, University of Ulm, Germany, September 2004.
Gerd Mayer, Jonas Melchert, Hans Utz, Gerhard Kraetzschmar, and Günther Palm. Neural object classi_cation and tracking. In Proceedings of the IEEE SMC UKRI Chapter Conference 2005 on Applied Cybernetics, London, United Kingdom, September 2005. IEEE Systems, Man and Cybernetics Society, United Kingdom and Republic of Ireland Chapter.
T. Schmitt, M. Beetz, R. Hanek, and S. Buck. Watch their moves: Applying probabilistic multiple object tracking to autonomous robot soccer. In The Eighteenth National Conference on Artificial Intelligence, Edmonton, Alberta, Canada, 2002.
Thorsten Schmitt, Robert Hanek, Michael Beetz, Sebastian Buck, and Bernd Radig. Cooperative probabilistic state estimation for vision-based autonomous mobile robots. IEEE Transactions on Robotics and Automation, 18(5), October 2002.
C. Kwok and D. Fox. Map-based multiple model tracking of a moving object. In Proc. of the RoboCup 2004 International Symposium, 2004.
Norman Weiss and Lars Hildebrand. An examplary robot soccer vision system. In CLAWAR/EURON Workshop on Robots in Entertainment, Leisure and Hobby, Vienna, Austria, December 2004.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mayer, G., Utz, H., Palm, G. (2006). Information Integration in a Multi-Stage Object Classifier. In: Levi, P., Schanz, M., Lafrenz, R., Avrutin, V. (eds) Autonome Mobile Systeme 2005. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-30292-1_27
Download citation
DOI: https://doi.org/10.1007/3-540-30292-1_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-30291-9
Online ISBN: 978-3-540-30292-6
eBook Packages: Computer Science and Engineering (German Language)