Examining the Fidelity of On-the-Fly Assembly Inspection With a Low-Cost RGB-D Camera

This paper examines the fidelity of a commodity range camera for assembly inspection in use cases such as augmented reality-based assembly assistance. The objective of inspection is to determine whether a part is present and correctly aligned. In our scenario, shortly after the mechanics assembled the part, which is denoted as on-the-fly inspection. Our approach is based on object tracking and a subsequent discrepancy analysis. Object tracking determines the presence, position, and orientation of parts. The discrepancy analysis facilitates to determine whether the parts are correctly aligned. In comparison to a naive position and orientation difference approach, the discrepancy analysis incorporates the dimensions of parts, which increases the alignment fidelity. To assess this, an experiment was conducted in order to determine the accuracy range. The results indicate a sufficient accuracy for larger parts a noticeable improvement in comparison to the naive approach.