[1]王年涛,王淑青,汤 璐,等. 基于EfficientNet-YOLOv5s的绝缘子缺陷检测[J].湖北工业大学学报,2023,(1):21-26.
　WANG Niantao,WANG Shuqing,TANG Lu,et al. Insulator Defect Detection Based on EfficientNet-YOLOv5s Network[J].,2023,(1):21-26.
点击复制

 基于EfficientNet-YOLOv5s的绝缘子缺陷检测()
分享到：

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
期数:
2023年第1期
页码:
21-26
栏目:
湖北工业大学学报
出版日期:
2023-03-13

文章信息/Info

Title:
 Insulator Defect Detection Based on EfficientNet-YOLOv5s Network
文章编号:
1003-4684(2023)01-0021-06
作者:
 王年涛;  王淑青;  汤 璐;  马 丹
 湖北工业大学电气与电子工程学院，湖北省 武汉市 430068
Author(s):
 WANG Niantao; WANG Shuqing; TANG Lu; MA Dan
 School of Electrical and Electronic Engin. , Hubei Univ. of Tech. ,Wuhan 430068, China
关键词:
 ; 绝缘子;  目标检测;  YOLOv5s;  EfficientNet
Keywords:
 ; insulator;  target detection;  yolov5;  efficientnet
分类号:
TP391.41
文献标志码:
A
摘要:
 针对目前复杂背景下绝缘子缺陷小目标检测准确率低的问题，提出一种深度学习框架下的EfficientNet-YOLOv5s神经网络检测算法，首先通过无人机航拍输电线路中含有各类绝缘子的图像，并通过图像增强技术丰富图像数据集，然后用EfficientNet网络替换YOLOv5s主干网络，用改进的网络对标注的绝缘子数据集进行训练和测试，最后对模型的损失函数和非极大值抑制算法加以改进，进一步解决绝缘子目标重叠导致的漏检问题。实验结果表明，改进的网络平均精度达到98.5%，满足输电线路中绝缘子缺陷检测要求。
Abstract:
 Aiming at the problem of low detection accuracy of small target of insulator defect in complex background at present, an EfficientNet-YOLOv5s neural network detection algorithm based on deep learning framework is proposed. Firstly, the images of various insulators in the transmission line are aerial taken by UAV, and the image data set is enriched by image enhancement technology. Then, the EfficientNet network is used to replace the YOLOv5s backbone network. The improved network is used to train and test the labeled insulator data set. Finally, the non-maximum suppression algorithm and loss function of the model are improved to further solve the problem of missing detection caused by overlapping insulator targets. The experimental results show that the mAP of the improved network reaches 98.5%, which meets the requirements of insulator defect detection in transmission lines.

参考文献/References:

[1] 金光. 基于纹理频谱的电气化铁路绝缘子劣损状态检测[J]. 自动化与仪器仪表, 2021(06): 22-25，30.
[2] 易继禹, 陈慈发, 龚国强. 基于改进Faster RCNN的输电线路航拍绝缘子检测[J]. 计算机工程, 2021, 47(06): 292-298，304.
[3] 唐波, 覃乔, 黄力. 基于色彩模型和纹理特征的输电线路绝缘子串航拍图像识别[J]. 电力科学与技术学报, 2020, 35(04): 13-19.
[4] TAN P, LI X, XU J, et al. Catenary insulator defect detection based on contour features and gray similarity matching[J]. Journal of Zhejiang University-Science A(Applied Physics & Engineering), 2020, 21(01): 64-73.
[5] 虢韬, 杨恒, 时磊, 等. 基于Faster RCNN的绝缘子自爆缺陷识别[J]. 电瓷避雷器, 2019(03): 183-189.
[6] 杨焰飞, 曹阳. 基于深度学习的无人机拍摄图像绝缘子目标检测[J]. 激光杂志, 2020, 41 (10):63-66.
[7] 张焕坤, 李军毅, 张斌. 基于改进型YOLOv3的绝缘子异物检测方法[J]. 中国电力, 2020, 53(02): 49-55.
[8] 郑伟, 杨晓辉, 吕中宾, 等. 基于改进YOLOv4输电线关键部件实时检测方法[J]. 科学技术与工程, 2021, 21(24): 10 393-10 400.
[9] 朱秀红. 基于深度卷积网络的输电线路变尺度多目标检测算法研究[D]. 武汉: 华中科技大学, 2019.
[10] 刘悦, 黄新波. 基于YOLOv4和改进分水岭算法的绝缘子爆裂检测定位研究[J]. 电网与清洁能源, 2021, 37(07): 51-57.
[11] TAO X, ZHANG D, WANG Z, et al. Detection of power line insulator defects using aerial images analyzed with convolutional neural networks[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2018, 50(04): 1486-1498.
[12] 王年涛, 王淑青, 张鹏飞, 等. 一种EfficientNet网络下雾天道路能见度估测方法[J].湖北工业大学学报, 2021, 36(05): 42-46.
[13] 李景琳, 姜晶菲, 窦勇, 等. 基于Soft-NMS的候选框去冗余加速器设计[J]. 计算机工程与科学, 2021, 43(04): 586-593.
[14] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(09): 1904-1916.

相似文献/References:

[1]熊韧,曹海印,王焱清,等.非牛顿润滑静压轴承的节流器流量方程修正[J].湖北工业大学学报,2019,34(5):6.
　XIONG Ren,CAO Haiyin,WANG Yanqing,et al.Modified restrictor flow equations of hydrostatic bearings ubricated by non-Newtonian fluids[J].,2019,34(1):6.
[2]王照远,曹 民,王 毅,等. 场景与数据双驱动的隧道图像拼接方法[J].湖北工业大学学报,2020,(4):11.
　WANG Zhaoyuan,CAO Min,WANG Yi,et al. Tunnel Image Stitching Method based on Scene and Data[J].,2020,(1):11.
[3]潘 健,梁佳成,陈凤娇,等. 单电流闭环多重PR控制的LCL型逆变器[J].湖北工业大学学报,2020,(4):16.
　PAN Jian,LIANG Jiacheng,CHEN Fengjiao,et al. Design of LCL Grid Connected Inverter based on Single Closed Loop Control and Multiple PR Controllers[J].,2020,(1):16.
[4]王晓光,赵 萌,文益雪,等. 定子闭口槽结构对永磁电机齿槽转矩影响分析[J].湖北工业大学学报,2020,(4):25.
　WANG Xiaoguang,ZHAO Meng,WEN Yixue,et al. Study on Cogging Torque and Vibration Noise of Permanent Magnet Motor with Segmental Stator and Closed-Slot[J].,2020,(1):25.
[5]宇 卫,凃玲英,陈 健. 风电场集中接入对集电线电流保护的影响[J].湖北工业大学学报,2020,(4):29.
　YU Wei,TU Lingying,CHEN Jian. Effect of the Collective Line Current Protection when Wind Farms are Centralized Accessed to the Power System[J].,2020,(1):29.
[6]廖政斌,王泽飞,祝 珊. 二惯量系统谐振在线抑制及相位补偿[J].湖北工业大学学报,2020,(4):34.
　LIAO Zhengbin,WANG Zefei,ZHU Shan. Online Resonance Suppression and Phase Compensation for Double Inertia System[J].,2020,(1):34.
[7]王 欣,游 颖,姜天翔,等. 面向3D打印过程的产品工艺设计和优化[J].湖北工业大学学报,2020,(4):39.
　WANG Xin,YOU Ying,JIANG Tianxiang,et al. Product Process Design and Optimization for 3D Printing Processes[J].,2020,(1):39.
[8]冉晶晶,文 红,罗雅梅,等. 全自动样品前处理平台及其控制系统[J].湖北工业大学学报,2020,(4):43.
　RAN Jingjing,WEN Hong,LUO Yamei,et al. Research on Automatic Sample Preprocessing Platform and its Control System[J].,2020,(1):43.
[9]杨 磊,马志艳,石 敏,等. 基于模糊PID的小型冷库过热度控制方法[J].湖北工业大学学报,2020,(4):43.
　YANG Lei,MA Zhiyan,SHI Min,et al. Research on Superheat Control Method of Small Cold Storage based on Fuzzy PID[J].,2020,(1):43.
[10]黄 晶,周细枝,周业望. 动态注塑成型模具的设计与实验研究[J].湖北工业大学学报,2020,(4):52.
　HUANG Jing,ZHOU Xizhi,ZHOU Yewang. Design and Experimental Study of Dynamic Injection Molding[J].,2020,(1):52.

备注/Memo

备注/Memo:
［收稿日期］ 2021-12-27
［第一作者］ 王年涛（1995年-），男，湖北黄冈人，湖北工业大学硕士研究生，研究方向为电气工程
［通信作者］ 王淑青（1969年-），女，河北衡水人，湖北工业大学教授，研究方向为智能检测与控制
更新日期/Last Update: 2023-03-14