Conditional generative adversarial network-based training image inpainting for laser vision seam tracking. (November 2020)

• Record Type: Journal Article
• Authors: Zou, Yanbiao; Wei, Xianzhong; Chen, Jiaxin
• Is Part Of: Optics and lasers in engineering. Volume 134(2020)
• Publication Date: 2020-11
• Subjects: Automatic welding -- Conditional generative adversarial network -- Training image inpainting -- Welding robot -- Welding seam tracking; Lasers in engineering -- Periodicals; Optical measurements -- Periodicals; Optics -- Periodicals; Lasers en ingénierie -- Périodiques; Mesures optiques -- Périodiques; Optique -- Périodiques; 621.36605
• DOI: 10.1016/j.optlaseng.2020.106140
• Languages: English
• ISSNs: 0143-8166

Abstract

Highlights: A novel method is proposed to overcome the interference of strong noise during welding process. A welding image inpainting network is constructed to decontaminate training data for seam tracking model in real time. With a structured light vision system, a specifically designed sampling method is adopted to collect training images for training a robust inpainting network. To realize automatic seam tracking, a welding image inpainting tracking method by embedding the inpainting network into an efficient convolution operators (ECO) tracker is proposed, which significantly enhances the robustness of the tracking model and improves seam tracking accuracy. Abstract: In the process of welding seam tracking based on laser vision, the location accuracy of the seam largely depends on the quality of the welding image training samples acquired in real time. However, the interference of a strong arc, spatter, and other noise in the welding process seriously contaminate the training images, which can cause tracking model drift and result in tracking failure. To enhance the robustness of the seam tracking model and improve the welding accuracy, a welding image inpainting method based on a conditional generative adversarial network (CGAN) is proposed. We constructed a welding image inpainting network and defined a loss function for the network training. Through training, the network learns an end-to-end mapping from a noisy welding image to the corresponding noise-free image. Then, to realize accurate automatic seam tracking, the optimized inpainting network was integrated into a tracker for training sample restoration, which improves the antinoise interference performance of the seam tracking system. The experimental results show that the proposed seam tracking method can stabilize the average welding error within 0.2 mm, which is superior to the existing methods. This demonstrate the effectiveness of the proposed method for improving the robustness and welding accuracy of the seam tracking system.