Multiframe resolution-enhanced autostereoscopic system for on-machine 3-D surface metrology

Abstract

This article presents a multiframe (MF) resolution-enhanced autostereoscopic system for the on-machine measurement of 3-D surfaces. It takes advantage of the vibration from the machine tool during the on-machine measurement process to acquire multiple frames of the target surface with offsets, thereby achieving resolution enhancement. A MF resolution-enhanced deep-learning model is developed to generate resolution-enhanced raw elemental images which significantly improve the measurement resolution of the system. The performance of the system is evaluated by experiments and the results show that the spatial resolution of the measurement data is enhanced four times with improved measurement accuracy.