To meet the demand for seam tracking of welding robots, a deep learning-based framework called DeepKP is proposed in this article, which aims to precisely extract weld seam keypoints (WSKPs) under multiple arc light interference. DeepKP comprises a keypoint extraction model named WeldExt and a denoising model named WeldDenoise. WeldExt is proposed to identify weld seam types, obtain prior box region (PBR), and then extract keypoints in the region. WeldExt addresses the problem that most recent extraction models cannot directly obtain the keypoints. WeldDenoise is proposed for denoising weld seam images affected by multiple arc light interference, which overcomes the limitation that most recent denoising models must use paired datasets for training. Experiment results show that the average locating error of WSKP in WeldExt is 1.75 pixels and the average seam tracking error of DeepKp is 0.336 mm. Therefore, DeepKP performs excellently in extracting WSKPs under challenging arc light conditions and improves the quality of seam tracking.

中文翻译：

---

DeepKP：用于焊接机器人焊缝关键点提取的稳健而准确的框架

为了满足焊接机器人的焊缝跟踪需求，本文提出了一种基于深度学习的框架DeepKP，旨在在多重弧光干扰下精确提取焊缝关键点（WSKP）。 DeepKP 由名为 WeldExt 的关键点提取模型和名为 WeldDenoise 的去噪模型组成。 WeldExt 被提出来识别焊缝类型，获得先验框区域（PBR），然后提取该区域中的关键点。 WeldExt解决了目前大多数提取模型无法直接获取关键点的问题。 WeldDenoise 是针对受多重弧光干扰影响的焊缝图像进行去噪，克服了最新去噪模型必须使用配对数据集进行训练的限制。实验结果表明，WeldExt中WSKP的平均定位误差为1.75像素，DeepKp的平均焊缝跟踪误差为0.336 mm。因此，DeepKP 在具有挑战性的弧光条件下提取 WSKP 方面表现出色，并提高了焊缝跟踪的质量。