Accurate profile measurement method for industrial stereo-vision systems

Abstract

Purpose Profile measurement with boundary information plays a vital role in the detection of quality in the assembly of aviation parts. The purpose of this paper is to improve the evaluation accuracy of the aerodynamic shapes of airplanes, the profiles of large-sized parts need to be measured accurately. Design/methodology/approach In this paper, an accurate profile measurement method based on boundary reference points is proposed for the industrial stereo-vision system. Based on the boundary-reference points, the authors established a priori constraint for extracting the boundary of the measured part. Combining with the image features of background and the measured part, an image-edge compensation model is established to extract the boundary of the measured part. The critical point of a laser stripe on the edge of the measured part is extracted corresponding to the boundary constraint. Finally, as per the principle of binocular vision, the profile of the measured part is reconstructed. Finding Laboratory experiments validate the measurement accuracy of the proposed method which is 0.33 mm. In the analysis of results between the measured data and the theoretical model, the measuring accuracy of the proposed method was found to be significantly higher than that of the other traditional methods. Practical implication An aviation part was measured in the part-assembly shop by the proposed method, which verified the feasibility and effectiveness of this method. The research can realize the measurement of smooth surface boundary which can solve existing profile reconstruction problems for aviation parts. Originality/value According to the two-dimensional contour constraint, critical points of the laser strip sequence at the edge of measured part are extracted and the accurate profile reconstruction with the boundary is realized.