Automatic accurate longitudinal location of structural defects in sewer pipes via monocular ranging

Abstract

Rough manual interpretation distance cannot keep up with the intelligent detection and interpretation of sewer pipe defects. We present an automatic location method for the accurate longitudinal distance of the structural defects in sewer pipes via a pinhole-based defect monocular ranging model via image processing of pipe diameters. Then the model verification experiment is undertaken through a comparison with the actual data of the pipe size and the camera parameters. The results of the experiment demonstrate an improved accuracy of this method of defect spatial location and the robustness and stability of the model of the accurate acquisition of the longitudinal distance based on the monocular ranging between the inspection robot and the pipe defect.