The invention relates to the technical field of intelligent
welding, in particular to a steel structure
fillet weld intelligent identification method and
system based on 3D vision, and the method comprises the steps: obtaining a
point cloud data set of a workpiece, and extracting
point cloud data of a weld region from the
point cloud data set; dividing the
welding seam area into a plurality of
welding seam sub-areas, wherein one welding seam sub-area corresponds to one independent welding seam; carrying out welding seam coarse skeleton extraction on each welding seam sub-region, and carrying out merging
processing on the welding seam coarse skeletons of which the distance between end points is smaller than a threshold value; and on the basis of the combined welding seam coarse skeletons, welding seam fine skeleton
point set extraction is conducted, and a welding seam
path expression is obtained based on welding seam fine skeleton
point set fitting. The method solves the problem that an existing
algorithm needs an operator to repeatedly adjust a threshold parameter according to experience, resulting in lack of adaptive ability, and solves the problems that the calculated amount is large, the speed is low and the real-time requirement of an
industrial site cannot be met when the workpiece point
cloud data is processed.