Abstract
During the last few years a wide range of algorithms and devices have been made available to easily acquire range images. To this extent, the increasing abundance of depth data boosts the need for reliable and unsupervised analysis techniques, spanning from part registration to automated segmentation. In this context, we focus on the recognition of known objects in cluttered and incomplete 3D scans. Fitting a model to a scene is a very important task in many scenarios such as industrial inspection, scene understanding and even gaming. For this reason, this problem has been extensively tackled in literature. Nevertheless, while many descriptor-based approaches have been proposed, a number of hurdles still hinder the use of global techniques. In this paper we try to offer a different perspective on the topic. Specifically, we adopt an evolutionary selection algorithm in order to extend the scope of local descriptors to satisfy global pair wise constraints. In addition, the very same technique is also used to shift from an initial sparse correspondence to a dense matching. This leads to a novel pipeline for 3D object recognition, which is validated with an extensive set of experiments and comparisons with recent well-known feature-based approaches.
