3D Scanning Vision System Design and Implementation in Large Shipbuilding Environments

Abstract

To achieve efficient and intelligent welding of common workpieces such as subassemblies without relying on models, and to adapt to the unique large manufacturing scenes of the shipbuilding industry, 3D area-array cameras were used in this study instead of traditional line laser scanning sensors. Based on 3D vision processing technologies such as multisensor data calibration and point cloud registration, the 3D reconstruction and weld reconstruction vision system was designed for large scenes in shipbuilding, and the algorithm was optimized from the perspective of improving scanning efficiency and scanning accuracy. Through 3D scanning reconstruction and weld reconstruction tests on typical ship workpieces in large scenes, it was verified that the vision system in this paper can markedly improve scanning efficiency and scanning accuracy in large scenes, and provide efficient and accurate visual data support for intelligent welding of common workpieces such as subassemblies.