Abstract
Uncertain factors such as environmental noise and light source fluctuation will cause the loss of important features of the detection object, which will interfere with the detection and reconstruction accuracy. Therefore, accurate extraction of groove information is the key to ensure the quality of subsequent processes when detection technology is applied to steel structure grooves in ships, buildings, transportation and other fields. This paper designs a complex shaped detection and reconstruction algorithm based on linear structured light. This algorithm performs the visually assisted localization of the ROI area of the welding groove in a complex environment, and completes the extraction of the characteristic area of the welding groove and the interpolation of missing parts based on the slope method. According to the obtained information, the digital modeling analysis of each groove section feature is carried out, and the 3D model is reconstructed based on the feature information fitting. The extraction of geometric characteristics of single V-groove and the reconstruction of the 3D model are realized, and the effectiveness of the extracted geometric characteristics is verified. On this basis, the subsequent welding is completed well, which verifies that the algorithm can effectively reduce the influence of the lack of groove characteristics caused by uncertain factors.
