Pipe Defect Detection and Reconstruction Based on 3D Points Acquired by the Circular Structured Light Vision

Abstract

The inspection of pipe inside is very important so as to ensure the safety of pipe transmission. The pipe defect detection method based on inside 3D points acquired by circle structured light vision system was discussed in this paper. Based on the characteristics of 3D points inside a pipe acquired by circle structured light, a method by which pipe inner surface convex defect and pit defect were identified by the normal vector angle between adjacent points change on the same circle was proposed. A distance constraint between each pair of corresponding adjacent two points was proposed in order to recognize holes in the pipe inside. Based on Delaunay triangulation principle, the triangulation method for pipe inner surface circle structured light vision 3D points with hole and without hole was discussed and 3D reconstruction of the pipe was then realized. On the VC++ 6.0 software platform, pipe inner surface defect simulation data, hole simulation data and real 3D data were used to test the correctness of pipe defect identification method.