改进YOLOv8-Pose的钢筋焊接节点识别  

Improvement of YOLOv8-Pose for Identification of Steel Bar Welding Joints

作　　者：成彬 张博豪 雷华[2] CHENG Bin;ZHANG Bo-hao;LEI Hua(School of Mechanical and Electrical Engineering,Xi’an University of Architecture and Technology,Xi’an 710055,China;China Heavy Machinery Research Institute Corporation,Xi’an 710016,China)

机构地区：[1]西安建筑科技大学机电工程学院,陕西西安710055 [2]中国重型机械研究院股份公司,陕西西安710016

出　　处：《计算机技术与发展》2025年第2期174-182,共9页Computer Technology and Development

基　　金：陕西省自然科学基础研究计划项目(2021JM-360);国家自然科学基金(52475531)。

摘　　要：为解决光照不足、复杂路面背景和节点密集情况下钢筋骨架自动焊接成型中节点漏检、焊点位置不精确等难识别问题,借鉴人体姿态估计算法,提出了一种改进YOLOv8n-Pose的钢筋节点识别和焊点检测方法。首先,使用VanillaBlock代替网络中的3×3下采样卷积,在不降低模型精度的同时减少了模型复杂度;然后,在Neck中的C2f模块中嵌入VanillaBlock,增强多尺度信息融合能力;最后,引入CoT注意力机制,提升在弱光下的节点检测能力。实验结果表明,改进后YOLOv8n-Pose算法mAP 0.5-kp为90.2%,mAP 0.5:0.95-kp为89.5%,相比于原模型均提高了3.7百分点,单张图像平均检测时间为20.9 ms。与HRNet-s、RTMpose-s、YOLOv5n-Pose和YOLOv7t-Pose检测网络相比,mAP 0.5-kp分别提升了3.2百分点、5.0百分点、16.0百分点、13.1百分点。改进YOLOv8n-Pose对背景复杂、光照不足和节点密集等情况具有较高的检测精度,能够满足自动化钢筋骨架焊接成型的实时检测需求。To address the challenges of under-illumination,complex backgrounds,and dense node scenarios in the automatic welding forming of rebar frameworks,leading to missed detection of nodes and inaccurate positioning of welding points,a method based on an improved YOLOv8n-Pose for rebar node recognition and welding point detection is proposed by drawing on human pose estimation algorithms.Firstly,VanillaBlock replaces the 3×3 down-sampling convolution in the network,reducing model complexity without decreasing model accuracy.Then,VanillaBlock is embedded in the C2f module in the Neck,enhancing multi-scale fusion capability.Finally,the introduction of the CoT attention mechanism improves node detection capability under weak light.Experimental results show that the improved YOLOv8n-Pose algorithm achieves an mAP 0.5-kp of 90.2%and an mAP 0.5:0.95-kp of 89.5%,both increasing by 3.7 percentage points compared to the original model,with an average detection time of 20.9 ms per image.Compared with the HRNet-s,RTMpose-s,YOLOv5n-Pose,and YOLOv7t-Pose detection networks,mAP 0.5-kp increased by 3.2 percentage points、5.0 percentage points、16.0 percentage points and 13.1 percentage points,respectively.The improved YOLOv8n-Pose demonstrates high detection accuracy in complex backgrounds,insufficient light,and dense node scenarios,meeting the real-time detection needs of automated rebar framework welding.

关 键 词：钢筋焊点检测 CoT注意力机制 VanillaNet YOLOv8-Pose 关键点检测 目标检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TU755.32[自动化与计算机技术—计算机科学与技术]