Defect detection method using laser vision with model-based segmentation for laser brazing welds on car body surface

Abstract This paper proposes a defect detection method using laser vision with model-based segmentation for laser brazing welds on car body surface, in which a dynamic ideal surface (DIS), composed of a series of dynamic ideal contours (DIC), is first established for welding surface. The DIC model is obtained by dynamically fitting welding surface contours using the weighted cubic spline regression (WCSR) model with the fast Expectation-Maximization (Fast-EM) algorithm. Then through multi-threshold analysis on the DIC model residuals, whether the contour is defective and the nature of defect can be identified, and finally the defect can be completely separated. The whole process is fully automatic and requires no prior knowledge of defect. Experimental results show that the model-based segmentation method has managed to separate multiple types of defect effectively while meeting the actual accuracy requirements. The robustness of the proposed method has been proved through the test in the case of noise interference and unstable movement of the sensor, which helps to realize online inspection of weld defects in a factory environment.