View Planning Approach for Automatic 3D Digitization of Unknown Objects

Abstract

This paper addresses the view planning problem for the digitization of 3D objects without prior knowledge on their shape and presents a novel surface approach for the Next Best View (NBV) computation. The proposed method uses the concept of Mass Vector Chains (MVC) to define the global orientation of the scanned part. All of the viewpoints satisfying an orientation constraint are clustered using the Mean Shift technique to construct a first set of candidates for the NBV. Then, a weight is assigned to each mode according to the elementary orientations of its different descriptors. The NBV is chosen among the modes with the highest weights and which comply with the robotics constraints. Eventually, our method is generic since it is applicable to all kinds of scanners. Experiments applying a digitization cell demonstrate the feasibility and the efficiency of the approach which leads to an intuitive and fast 3D acquisition while moving efficiently the ranging device.

Finding the next-best scanner position for as-built modeling of piping systems

“…The next best sensor position is selected as the one among the periphery from which the sparse point density area on the object can be maximally captured. Similar studies are done by (Papadopoulos-Orfanos et al, 1997), (Reed et al, 1999), (Khalfaoui et al, 2012) where the completion of the 3D reconstruction of a small object is focused in NBV. (Pito, 1999) takes into account the scan overlap identification and tolerance constraints of the choice of the NBV in the similar context.…”

Aiding Grasp Synthesis for Novel Objects Using Heuristic-Based and Data-Driven Active Vision Methods

“…Our research focuses on this problem of collecting new data to improve processing outcomes. Active vision has been applied to many aspects of machine vision, but often with the explicit goal of completely viewing a 3D object (Khalfaoui et al, 2012;Daudelin and Campbell, 2017), rather than our objective of viewing just enough of the object to perform a grasp. Even in the narrower domain of active vision for grasp synthesis, not all work relates to our concerns.…”