A model-based 3-D vision system for bin-picking

A vision system to recognize 3-D objects in a scene and to evaluate their attitude is presented. This system uses a model-based approach to determine the attitude of 3-D industrial parts in the context of bin packing. It is based on the matching of the extended Gaussian image (EGI) extracted from the surface normal map (needle map) of an observed object with the EGI generated from a 3-D model using geometric modeling. It is shown that geometric modeling can be used to provide an object description (visible surface orientation referred to as a needle map) suited to the problem of 3-D object recognition and attitude evaluation.<
>