Spherical dual images: A 3D representation method for solid objects that combines dual space and Gaussian spheres

Three-dimensional object representation significantly impacts computations for manipulation, spatial reasoning and vision. This paper introduces a technique called the spherical dual image, derived from Gaussian sphere and dual space concepts. This representation technique will be defined and a number of its properties will be proven, leading to a reconstruction algorithm for convex and concave polyhedra. Finally, the application of this representation for selecting grasping points to manipulate a polyhedron is discussed.