ABSTRACT
In this chapter we present a new approach to recognize and locate partially occluded rigid objects from a given scene based on belief revision. We generate a belief about
the scene using assumption-based truth maintenance (ATM) system. The ATM system is basically a tool for belief revision. It explores multiple potential solutions and can work out efficiently with inconsistent information. In practice, sometimes occlusion of objects in a 2D scene may occur due to the presence of objects which are not described in our primary knowledge base and which may appear to be an object, in addition to the model objects of our primary knowledge base. Hence, after detection of such an event, question of revising belief about the scene may arise to establish a new belief. The present approach [66] to recognize and locate an occluded scene is completely different from the existing paradigm based on the concept of hypothesis generation and verification which is already discussed.
