A NONITERATIVE PROBABILISTIC METHOD FOR CONTEXTUAL CORRESPONDENCE MATCHING

In this paper, we develop a framework for non-iterative structural mat ching using contextual information. It is based on Bayesian reasoning and involves the explicit modelling of the binary relations between th e objects. The difference between this and previously developed theori es of the kind lies in the assumption that the binary relations used a re derivable from the unary measurements that refer to individual obje cts. This leads to a non-iterative formula for probabilistic reasoning which is amenable to real-time implementation and produces good resul ts. The theory is demonstrated using two applications, one on stereo m atching of linear features and the other on automatic map registration . The breaking points of the theory are also identified experimentally and the situations under which the proposed algorithm is applicable a re discussed. (C) 1998 Pattern Recognition Society. Published by Elsev ier Science Ltd. All rights reserved.