Automatic view planning with self-termination in 3D object reconstructions

Viewpoint planning plays an important role in automatic 3D model reconstruction. The objective of view planning in a visual sensing system is to make task-directed decisions for optimal sensing pose selection. In this paper we present a method of view planning for automatically constructing the model of an unknown object from range images. The method computes the next best view in two steps. First, the exploration direction for the next view is determined via a mass vector chain (MVC) based scheme. Then the accurate position of the next view is obtained by computing the boundary integral of the vectors fields. The position with the maximum integral value is selected as the next best view (NBV). We also present a self-termination criterion for judging the completion condition in the measurement and reconstruction process. The termination condition is derived based on changes in the volume computed from two successive viewpoints. The experimental results show that the method is effective in practical implementation.