基于IND-YOLO网络的绝缘子多缺陷检测算法研究  

Insulator Multi-defect Detection Algorithm Based on IND-YOLO Network

作　　者：陈里里 张程旺 赵鑫 杨维川 CHEN Lili;ZHANG Chengwang;ZHAO Xin;YANG Weichuan(School of Information Science and Engineering,Chongqing Jiaotong University,Chongqing 400074,China;School of Mechatronics and Vehicle Engineering,Chongqing Jiaotong University,Chongqing 400074,China)

机构地区：[1]重庆交通大学信息科学与工程学院,重庆400074 [2]重庆交通大学机电与车辆工程学院,重庆400074

出　　处：《重庆交通大学学报(自然科学版)》2025年第4期28-36,共9页Journal of Chongqing Jiaotong University(Natural Science)

基　　金：重庆市技术创新与应用发展专项重点项目(CSTB2022TIAD-KPX0075);交通工程应用机器人重庆市工程实验室2020年度开放课题项目(CELTEAR-KFKT-202003);重庆市社会事业与民生保障科技创新专项项目(cstc2017shmsA30016)。

摘　　要：针对绝缘子多缺陷检测易发生漏检、错检以及误检等问题。提出一种基于改进YOLOv8算法的IND-YOLO绝缘子缺陷检测算法。通过结合可变形卷积Dcnv2和网络中的C2f结构,可降低算法参数并更注重绝缘子缺陷多变的特征。采用CA(coord attention)注意力机制提升对感兴趣区域的特征提取能力。考虑到模型检测小目标缺陷能力不足的情况,IND-YOLO算法增加了浅层输出。利用Siou损失函数加快模型收敛速度。实验结果表明:该模型检测平均精度M ap@50达到0.943,较基准模型提升了5.6%,F 1分数(F 1score)达到0.92,较YOLOv8算法提升了4.6%,且检测速度F PS可以达到62帧/s。该模型的提出在绝缘子多缺陷检测中具有较广泛的应用前景。Regarding the issue of missed,erroneous,and false detections in the detection of multiple defects in insulators,an IND-YOLO insulator defect-detection algorithm based on improved YOLOv8 algorithm was proposed.By combining the deformable convolution Dcnv2 and the C2f structure in the network,the algorithm parameters could be reduced,and more attention could be paid to the variable characteristics of insulator defects algorithm.The coord attention attention mechanism was used to improve the feature extraction ability of the region of interest.Considering the insufficient ability of the model to detect small target defects,IND-YOLO algorithm added shallow output.The Siou loss function was used to accelerate the convergence speed of the model.The experiment results show that the average detection accuracy M ap@0.5 of the proposed model reaches 0.943,which is 5.6%higher than that of benchmark model.The F 1score reaches 0.92,which is 4.6%higher than that of YOLOv8,and the detection speed can reach 62 frames per second.The proposed model has a wide application prospect in insulator multi-defect detection.

关 键 词：交通运输工程 电气化铁路 绝缘子 YOLOv8算法 可变形卷积 小目标 

分 类 号：U225.43[交通运输工程—道路与铁道工程] TP391[自动化与计算机技术—计算机应用技术]