Deformation visual inspection of industrial parts with image sequence

A new approach to reconstructing and inspecting the deformation of industrial parts, especially sheetmetal parts based on CAD-designed data and hybrid point-line bundle adjustment with image sequence, is proposed. Nonmetric image sequence and CAD-designed data of parts are used as the source of information. The strategy of our approach is to reconstruct and inspect deformations of parts automatically with image points and line segments extracted from the images. Basic error equation of line photogrammetry and its modified form are addressed in detail. It is shown that when a certain proper weight is selected, adjustment by condition equations and adjustment by observation equations are equivalent for line photogrammetry. A novel hybrid point-line bundle adjustment algorithm is used to reconstruct industrial parts. The proposed hybrid adjustment model can be used in various 3D reconstruction applications of objects mainly composed of points and lines. The developed inspection system is tested with true image data acquired by a CCD camera, and the results are very satisfying.