Integration of different computational models in a computer vision framework

A general (application independent) computer vision framework is proposed. It follows the methodology of knowledge-base systems - dividing a system into knowledge base and control. We choose procedural semantic networks for object-oriented modelling of the world. It is basically a non-monotonic logical system. Several inference rules are proposed that allow to create instances of model concepts. In order to activate an inference rule a model-to-image data matching process need to be performed. We view this matching as a solution to constraint satisfaction problem (CSP), supported by Bayesian net-based evaluation of partial variable assignments. A modified incremental search for CSP is designed that allows partial solutions and calls for stochastic inference in order to provide judgments of partial states. Hence the detection of partial occlusion of objects is handled consistently with Bayesian inference over evidence and hidden variables.