基于改进YOLOv8s的网线接线缺陷检测算法  

An Improved YOLOv8s-based Algorithm for Network Cable Wiring Defect Detection

作　　者：李文锋 陆施楷 李春阳 邓粤昊 王琪琪 LI Wenfeng;LU Shikai;LI Chunyang;DENG Yuehao;WANG Qiqi(Jinling Institute of Technology,Nanjing 211169,China)

机构地区：[1]金陵科技学院软件工程学院,江苏南京211169

出　　处：《金陵科技学院学报》2025年第1期1-7,共7页Journal of Jinling Institute of Technology

基　　金：金陵科技学院高层次人才科研启动项目(jit-b-202109);江苏省产学研合作项目(BY20230682);金陵科技学院校级“科教融合”项目(2024KJRH16);金陵科技学院校级教育教改研究课题(JYJG202322);国家档案局科技项目(2023-X-024)。

摘　　要：针对人工检查机柜网线接线缺陷时工作量大、效率不高等问题,提出了一种基于改进YOLOv8s的网线接线缺陷检测算法。首先,针对目前网线接线缺陷检测尚无公开数据集的问题,本文构建了由640个小样本组成的网线接线缺陷数据集;其次,为了提升小目标检测效果,在模型中增加P2检测层,强化了对细粒度特征的捕捉;最后,提出了C3f模块,并用C3f模块替换原YOLOv8s模型中骨干网络的C2f模块,进一步增强了模型对局部特征的表征能力。实验结果表明,改进后的YOLOv8s模型的mAP^(val) 50-95指标达85.2%,与YOLOv8s模型相比,精度提升了2.8个百分点,跟其他模型相比,能够更有效识别网线接线缺陷。To solve the problems of heavy workload and low efficiency in manually inspecting network cable wiring defects in cabinets,an improved YOLOv8s-based algorithm for network cable wiring defect detection is proposed.Firstly,in response to the lack of a public dataset for network cable wiring defects detection,this paper constructs a network cable wiring defect dataset consisting of 640 small samples.Secondly,in order to improve the detection performance of small targets,a P2 detection layer is added to the model to enhance the capture of fine-grained features.Finally,a C3f module is proposed and replaces the C2f module in the backbone network of the original YOLOv8s model,further enhancing the model's ability to represent local features.The experimental results show that the improved YOLOv8s model achieves 85.2%on the mAP^(val) 50-95 index,with an improvement of 2.8 percentage points in accuracy compared to the YOLOv8s model.Compared to other models,it can more effectively identify network cable wiring defects.

关 键 词：YOLOv8s 小目标检测 网线 缺陷检测 C3f模块 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]