Object locating based on concentric circular description

Abstract

The authors propose a simple method for locating a 3D object from a single 2D image. Aiming at rough and speedy location of a target object, the method simply checks shape similarity between observed regions and possible appearances of the target. To reduce the number of the appearances necessary for representing an object, the authors develop a 2D shape description, called concentric circular description, which is insensitive to viewpoint changes while keeping a sensitivity to 3D shape difference. The method is applied to some real images of a cluttered desk scene.<>