PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A reasoning system to track movements of totally occluded objects
Martin Antenreiter and Peter Auer
In: Second International Cognitive Vision Workshop (ICVW06), 13 May 2006, Graz, Austria.


We present a system which is able to track objects under partial and total occlusion. The occlusion and movement reasoning uses abstract object descriptions for inference and is based on an extendable knowledge-base. The system manages various hypotheses about where objects could be and where they could reappear. It is able to deal with occlusion, noise and low-level vision failure. Our system uses a top-down approach, and is an initial step to integrate topdown and bottom-up processing of visual information.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:2379
Deposited By:Martin Antenreiter
Deposited On:22 November 2006