ECAI 2004 Conference Paper

[PDF] [full paper] [prev] [tofc] [next]

Using Spatio-Temporal Continuity Constraints to Enhance Visual Tracking of Moving Objects

Brandon Bennett, Derek R. Magee, Anthony G. Cohn, C. Hogg, David

A framework is presented for the logical and statistical analysis of dynamic scenes containing occlusion and other uncertainties. This framework consists of three elements: an object tracker module, an object recognition/classification module and a logical consistency reasoning engine. The principle behind the object tracker and recognition modules is to reduce arror by increasing ambiguity, by mergin objects in close proximity and presenting multiple hypotheses. The reasoning engine deals with error, ambiguity and occlusion in a unified framework to produce a most likely hypothesis which is logically consistent over time, in respect of spatio-temporal continuity constraints. The system results in improved annotation over frame-by-frame methods. The framework has been implemented and applied successfully to the analysis of team sports video recorded a single fixed cammera.

Keywords: vision, tracking, spatio-temporal reasoning

Citation: Brandon Bennett, Derek R. Magee, Anthony G. Cohn, C. Hogg, David: Using Spatio-Temporal Continuity Constraints to Enhance Visual Tracking of Moving Objects . In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.922-926.


[prev] [tofc] [next]


ECAI-2004 is organised by the European Coordinating Committee for Artificial Intelligence (ECCAI) and hosted by the Universitat Politècnica de València on behalf of Asociación Española de Inteligencia Artificial (AEPIA) and Associació Catalana d'Intel-ligència Artificial (ACIA).