3DComplete — Efficient 3D Completeness Inspection
One important application of machine vision is quality control and, in particular, checking the completeness (presence/ absence of parts, correct type, position, orientation, …) of assemblies.
Existing systems usually apply 2D cameras that provide a monochrome or colour image. These images lack the information of depth and consequently have problems when dealing with non-rigid objects (hoses, cables) or low contrast between background and part, whilst they often do not provide an optimal view on each single part of the assembly.
This project aims at developing efficient 3D completeness inspection methods that exploit two different technologies. The first one is based on calculating arbitrary views of an object given a small number of images of this object, the second one aims at combining 3D shape data with colour and texture information. Both technologies will cover the full chain, from data acquisition via pre-processing to the final decision-making by using standard hardware to create a cost-efficient technology.
Algorithms for 3D completeness inspection
Algorithms are currently under development that deal with the peculiarities of ortho-images and combined 3D data + colour information. Invariance to specific kinds of ‘noise’ and to motions in 6-degrees of freedom are being integrated in the system. Technology is based on correlation (2D) and spin image features (3D).