“…Liu et al (2012) presented a chamfer matching-based solution that extract depth edges via a multi-flash camera, while Sansoni, Bellandi, Leoni, and Docchio (2014) showed how a laser source scanning architecture can facilitate accurate pose estimation. In Buchholz, Kubus, Weidauer, Scholz, and Wahl (2014) inertial and visual data are fused to calculate grasp poses of testing objects (Kuo, Su, Lai, & Wu, 2014). In turn, in Nieuwenhuisen et al (2013) and Buchholz, Futterlieb, Winkelbach, and Wahl (2013) 3D descriptors (shape-based and spin images, respectively) are extracted from RGB-D input data and fed to nearest-neighbor classifiers to acquire accurate recognition and pose estimation results.…”