Recognizing and locating polyhedral objects from sparse range data

摘要

A model-based approach is described for recognizing and locatingpolyhedral objects from sparse light-stripe data. Based on two scans,consistent interpretations are provided by locating scanned linesegments on the faces of a set of known objects. The transformationassociated with each interpretation is estimated. Once all the feasiblemodels are transformed to the scene space, a strategy for additionalscanning positions is developed to distinguish the object uniquely