From image sequences to recognized moving polyhedral objects

摘要

This paper describes the combination of several novel algorithms into a system that obtains visual motion from a sequence of images and uses it to recover a three-dimensional description of the motion and geometry of the scene in terms of moving extended straight edges. The system goes on to recognize the recovered geometry as an object from a database of wireframe models, a stage that also resolves the depth/speed scaling ambiguity inherent in visual motion processing, resulting in absolute depth and motion recovery. The processing sequence is demonstrated on imagery from a well-carpentered CSG model and on natural imagery of simple polyhedral objects.