Abstract
Current research of binocular vision systems mainly need to resolve the camera’s intrinsic parameters before the reconstruction of three-dimensional (3D) objects. The classical Zhang’ calibration is hardly to calculate all errors caused by perspective distortion and lens distortion. Also, the image-matching algorithm of the binocular vision system still needs to be improved to accelerate the reconstruction speed of welding pool surfaces. In this paper, a preset coordinate system was utilized for camera calibration instead of Zhang’ calibration. The binocular vision system was modified to capture images of welding pool surfaces by suppressing the strong arc interference during gas metal arc welding. 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 values, pixel coordinates) was extracted as the feature vector of the welding pool surface. Based on the characteristics of the welding images, a mismatch-elimination algorithm was developed to increase the accuracy of image-matching algorithms. The world coordinates of matching feature points were calculated to reconstruct the 3D shape of the welding pool surface. The effectiveness and accuracy of the reconstruction of welding pool surfaces were verified by experimental results. This research proposes the development of binocular vision algorithms that can reconstruct the surface of welding pools accurately to realize intelligent welding control systems in the future.
Highlights
Gas metal arc welding (GMAW) is widely applied in modern manufacturing industries
In order to obtain the characteristic of scale invariance on the edges of the welding pool, the scale space was composed of four inner layers ci and four middle layers di(i=0,1,2,3) in the frame structure of binary robust invariant scalable keypoint (BRISK) feature detection
The world coordinates of the welding pool surface were reconstructed according to Section 3
Summary
Gas metal arc welding (GMAW) is widely applied in modern manufacturing industries. To improve the weld quality of manual GMAW, welders correct either the welding parameters or the position of welding gun based on information from the welding pool surface acquired by sight and their expertise [1]. Vasilev [5] utilized an ultrasonic thickness measurement system to control the welding current and welding speed These methods have mostly focused on improving the welding process with information from one-dimensional or two-dimensional welding pool surface data. A two-step stereo matching algorithm was proposed to reconstruct the 3D shape of the welding pool surface. The results were validated by a reconstructed standard cylinder with clear checkboard, yet the maximum height error was 4.15%, showing that the accuracy and usability of a global-based iterative matching algorithm for GMAW process without checkboard still needs to be verified and improved. The mathematical models including detection, description and matching of feature points were established to effectively and robustly calculate the world coordinates of welding pool surface against different welding conditions. If yp1=0.5i and yp2=0.5(i+1), the world coordinates were as follows: x
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
