基于改进YOLOv8的输电线路绝缘子缺陷检测方法  

Improved YOLOv8-based insulator defect detection method for transmission lines

作　　者：苏怡萱 李智[2] 盘书宝[2,3] Su Yixuan;Li Zhi;Pan Shubao(School of Electronic Engineering and Automation,Guilin University of Electronic Science and Technology,Guilin 541004,China;Guangxi Colleges and Universities Key Laboratory of UAV Systems and Technology Applications,Guilin University of Aerospace Technology,Guilin 541004,China;School of Electronic Information and Automation,Guilin University of Aerospace Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学电子工程与自动化学院,桂林541004 [2]桂林航天工业学院无人机系统与技术应用重点实验室,桂林541004 [3]桂林航天工业学院电子信息与自动化学院,桂林541004

出　　处：《电子测量与仪器学报》2025年第1期14-23,共10页Journal of Electronic Measurement and Instrumentation

基　　金：广西重点研发计划项目“自主管控和群体协同的机器人智慧巡防系统”(2023AB08117);桂林航天工业学院特色优势交叉学科发展战略研究专项(TS2024431)资助。

摘　　要：针对输电线路绝缘子缺陷检测过程中目标小、分布零散、易受背景及噪音干扰等问题,提出并改进了一种基于YOLOv8的输电线路绝缘子缺陷检测方法。首先引入了LSKNet代替原有的路径聚合网络,使模型能够根据不同目标的特性自适应地选取和调整卷积核的大小,从而在不同尺度上更精准地匹配目标特征与背景信息的需求,显著增强了对复杂场景下缺陷识别的鲁棒性;并进一步集成SPPF-LSKA模块,该模块通过融合全局上下文信息,极大提升了模型在多尺度特征上的聚合效率与分辨能力,为缺陷检测提供了更为精细的特征表示;此外,所提方法通过对YOLOv8的颈部网络中注入空域注意力机制,使其获得更强的全局特征理解力,强化了模型对关键信息,特别是对小目标的聚焦能力;同时,考虑到实际应用中的模型效率与部署问题,所提方法还将颈部网络中的部分常规卷积层替换为GhostConv,有效减少了模型的参数量和计算负担,实现了检测性能与资源效率的平衡优化。实验结果表明,所提方法的平均精度均值达到了93.1%,相较于改进前提升了4.4%。有效地实现了对小目标的精确检测。Aiming at the problems of small targets,scattered distribution,and susceptibility to background and noise interference in the process of transmission line insulator defect detection,an improved YOLOv8-based defect detection method is proposed.Firstly,LSKNet is introduced to replace the original path aggregation network,enabling the model to adaptively select and adjust convolution kernel sizes based on the characteristics of different targets.This allows for more precise matching of target features and background information at various scales,significantly enhancing the robustness of defect recognition in complex scenarios.Furthermore,the SPPF-LSKA module is integrated into the network.By fusing global context information,this module greatly improves the aggregation efficiency and discriminative capability of multi-scale features,providing more refined feature representation for defect detection.Additionally,the proposed method incorporates a spatial attention mechanism into the neck network of YOLOv8,enhancing the model’s global feature comprehension and strengthening its focus on key information,particularly for small targets.To address the practical requirements of model efficiency and deployment,part of the conventional convolution layers in the neck network are replaced with GhostConv,effectively reducing the model’s parameter count and computational overhead.This achieves a balance between detection performance and resource efficiency.Experimental results demonstrate that the proposed method achieves a mAP of 93.1%,representing a 4.4%improvement compared to the original model,effectively enabling accurate detection of small targets.

关 键 词：小目标检测 绝缘子缺陷 YOLOv8 注意力机制 深度学习 

分 类 号：TM93[电气工程—电力电子与电力传动] TP391.4[自动化与计算机技术—计算机应用技术]