Aiming at the current welding seam tracking problems such as susceptibility to arc light interference, low work efficiency, and poor real-time performance, a single-frame large-field welding seam positioning method combining polarization three-dimensional (3D) reconstruction and linear structured light imaging is proposed. Calculate the surface polarization state of the welding area through the polarization intensity images in four directions, use the degree of polarization and polarization angle to calculate the surface normal vector and integrate to obtain the relative depth value. Design a centerline extraction method based on skeleton extraction and Random Sample Consensus (RANSAC) to obtain the three-dimensional coordinates of the laser stripe. The three-dimensional coordinates of the laser fringe and the relative depth value of the polarization three-dimensional reconstruction are combined to calculate the real three-dimensional point cloud of the weld and the welded part. With this method, only a single frame of image data is acquired prior to welding and the coordinates of the 3D scene within the large field of view of the polarisation camera can be calculated, so there is no interference from arc light. For the weld within 100 mm, the 3D positioning accuracy is 0.2502 mm, which meets the requirements of weld positioning.