1986 年 1 巻 2 号 p. 219-227
A 3D vision system using a modeling with class concept has been constructed. The whole system is built based on the object-oriented programming paradigm,which has been very effective to implement a complex system incrementally. The models,which work as references in the understanding process,are represented as hierarchical composition of plane clusters,planes and line segments. For each hierarchical level,the models are defined from abstract description to specific one utilizing the inheritance function of the object-oriented programming. This model description allows an efficient coarse-to-fine understanding of 3D object from input image. The implemented system also has a function to supplement incomplete edge-lines caused by an illumination condition or occlusion.
