Using spin images for efficient object recognition in cluttered 3D scenes

TLDR

The spin image is a data‑level shape descriptor used to match surfaces represented as surface meshes. We present a 3D shape‑based object recognition system for simultaneous recognition of multiple objects in cluttered and occluded scenes. The system matches surfaces by matching points with spin image representations and employs a compression scheme that enables efficient simultaneous recognition of up to 20 models. The method achieves simultaneous recognition of multiple objects from a library of 20 models and demonstrates robust performance in cluttered and occluded scenes, as shown by trials on 100 scenes.

Abstract

We present a 3D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Recognition is based on matching surfaces by matching points using the spin image representation. The spin image is a data level shape descriptor that is used to match surfaces represented as surface meshes. We present a compression scheme for spin images that results in efficient multiple object recognition which we verify with results showing the simultaneous recognition of multiple objects from a library of 20 models. Furthermore, we demonstrate the robust performance of recognition in the presence of clutter and occlusion through analysis of recognition trials on 100 scenes.