Model invocation for three dimensional scene understanding

摘要

Any gantral model-based vision system must somehow select a few serious candidates from its model base before applying model-directed processing. This is necessary for both efficiency and recognising 'similar * models (i.e. handling data errors, generic models and previously unseen objects). This paper shows how one can Integrate knowledge of object properties, structural and generic relations to create a network computation that performs model invocation. The paper demonstrates successful invocation in a scene containing a self and externally obscured PUMA robot. 1 In trod net ion One important and difficult task for a general model based vision system is invoking the correct model. Because of the potentially huge number of possible objects, it is imperative that only a few serious