Three-dimensional reconstruction of welding pool surface by binocular vision

Abstract Welding pool geometry includes plenty of welding quality information. The observation and reconstruction of the welding pool surface is the basis of developing intelligent control system for welding process to substitute skilled welders. The binocular vision system was ameliorated to capture images of welding pool surface by suppressing the strong arc interference during gas metal arc welding (GMAW). Combining and improving the algorithms of speeded up robust features, binary robust invariant scalable keypoints and KAZE, the feature information of points (i.e. RGB value, pixel coordinates and so on) was extracted as the feature vector of the welding pool surface. Based on the characteristic of welding images, the mismatch elimination algorithm was developed to increase the accuracy of image matching algorithms. The world coordinates of matching feature points was calculated to reconstruct the 3D shape of the welding pool surface. The effectiveness and accuracy of reconstruction for welding pool surface were verified by the experimental results.