Automatic measurement of industrial sheetmetal parts with CAD data and non-metric image sequence

Abstract

A novel approach for three-dimensional (3D) reconstruction and measurement of industrial sheetmetal parts with computer aided design (CAD) data and non-metric image sequence is proposed. The purpose of our approach is to automatically reconstruct and measure the producing imprecision or deformations of industrial parts that are mainly composed of line segments, circles, connected arcs and lines. Principles of two-dimensional (2D) and one-dimensional (1D) least squares template matching to extract precise lines and points are presented. Hybrid point-line photogrammetry is adopted to obtain accurate wire frame model of industrial parts. Circles, arcs, and lines connected to each other on the part are reconstructed with direct object space solution according to known camera parameters. The reconstructed CAD model can be used for visual measurement. Experimental results of several parts are very satisfying. They show that the proposed approach has a promising potential in automatic 3D reconstruction and measurement of widely existed industrial parts mainly composed of lines, circles, connected arcs and lines.