Abstract
Weld recognition is the premise of automatic weld polishing, and weld image segmentation can provide key area information for robots. With the advent of large segmentation model, it will be more convenient to realize weld image segmentation. With the emergence of complex scenes such as smoke, how to achieve high precision weld image segmentation under different smoke concentrations has become a challenge. To solve this problem, we propose a lightweight weld segmentation approach in smoke scenes. The feature transformation can better realize the feature processing of the smoke weld image, and further combine with the large segmentation model to realize the smoke weld image segmentation. The experimental data show that the segmentation accuracy of the weld segmentation approach we proposed achieves 98.18% in everything mode, increasing by 0.67% and 11.64% compared with the typical comparison methods, respectively. And the feature transformation is relatively lightweight.