Vision-based measurement method for geometric dimensions of PVC pipe end faces

Abstract

This study introduces a vision-based expedited methodology for assessing various geometric circular dimensions on the termini of PVC conduits. The process commences with delineating pipe profiles using the EDPF algorithm for edge detection. Successive steps employ a radius-constrained weighted circular approximation algorithm to form provisional circular profiles from closed-edge segments. These profiles are refined using a rapid circle arc fitting algorithm for multiple open-edge sections. Noise circles are sifted out with the Number of False Alarms algorithm, and upon calibration with actual dimensions, these profiles are quantified into physical sizes of the conduit's terminal geometries. Empirical evidence from the methodology demonstrates an ability to measure the circular dimensions with a mean accuracy rate surpassing 99.2%.