ECAI 2004 Conference Paper

[full paper]

Qualitative Reasoning Feeding Back into Quantitative Model-based Tracking

Christian Köhler, Bernhard Nebel, Artur Ottlik, Hans-Hellmut Nagel

Tracking vehicles in image sequences of innercity road traffic scenes still must be considered to constitute a challenging task. Even if a-priori knowledge about the 3D form of vehicles, of the background structure, and about vehicle motion is provided, (partial) occlusion and dense vehicle queues easily can cause initialisation and tracking failures. A stepwise improvement of the tracking approach implies numerous and time-consuming experiments. These difficulties can be eased considerably by endowing the system with -- at least part of the -- qualitative knowledge which a human observer activates in order to judge the results. In the case to be reported here, a system for qualitative reasoning has been coupled with a quantiative model-based tracking system in order to explore the feedback from qualitative reasoning into the geometric tracking subsystem. The approach and encouraging experimental results obtained for real-world image sequences are described.

Keywords: Cognitive Vision, Model-based Tracking, Qualitative Reasoning

Citation: Christian Köhler, Bernhard Nebel, Artur Ottlik, Hans-Hellmut Nagel: Qualitative Reasoning Feeding Back into Quantitative Model-based Tracking. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.1045-1046.