Rapid invocation and matching of 3D models to 2D images using curvilinear data

Describes a practical approach to match 2D scenes to 3D models in which the scene data is described as a set of curvilinear features extracted from a grey scale image of a rigid object taken from an arbitrary viewpoint, and the model data is derived from a CSG modeller. In contrast to systems that directly acquire depth data, the low and intermediate processing is more reliable and less complex, which can lead to a more effective system using a rapid hypothesis and verification cycle. This may change as research in 3D increasingly concentrates on improving the sensor technology and low-level segmentation algorithms so that surface descriptions become less fragmented and include plausible curved surfaces