Robust 3D Object Registration Without Explicit Correspondence Using Geometric Integration
3D vision guided manipulation of components is a key problem of industrial machine vision. In this paper, the authors focus on the localization and pose estimation of known industrial objects from 3D measurements delivered by a scanning sensor. Because local information extracted from these measurements is unreliable due to noise, spatially unstructured measurements and missing detections, the authors present a novel objective function for robust registration without using correspondence information, based on the likelihood of model points. Furthermore, by extending Runge-Kutta type integration directly to the group of Euclidean transformation, they infer object pose by computing the gradient flow directly on the related manifold.