基于改进YOLOv8s的配电设备红外目标检测模型

Abstract
Figure/Table
References
Related Citation (2)

Download: PDF (3044 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract With the development of power inspection technology, using drones and infrared thermal imaging technology for inspection has become an important mode of power inspection operations. A target detection method for distribution equipment based on infrared images is proposed to address the issues of low recognition accuracy and difficulty in deploying large model parameters in current network models. Firstly, to address the problem of large parameter count and complex model in the original YOLOv8s model, it is proposed to replace some traditional Conv convolutions with GhostConv convolutions in the backbone network and Neck section to achieve model lightweight. Aiming at the problem of poor small target recognition ability in the original YOLOv8s model, it is proposed to add a small target detection layer to improve the detection ability of small targets. Finally, in response to the problem that the original YOLOv8s model loss function is not conducive to the prediction and regression of ordinary quality samples, a Wise-IoUv3 loss function is used to focus on the prediction and regression of anchor boxes that are difficult to fit during the training process. The research results show that the improved model has an accuracy of 87% which is 4.1% higher than that of the original model, a recall rate of 79.1% which is 3% higher than that of the original model, and a mean average precision (mAP) of 83.5% which is 1.5% higher than that of the original model. The inference speed is 62 ms/sheet. It can be effectively used for component detection in distribution equipment.

Key words： power distribution component inspection YOLOv8s infrared images small target detection layer GhostConv convolution Wise-IoUv3

Received: 17 November 2023

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WU Hefeng
	WANG Guowei
	WAN Zaojun
	ZHANG Kuo
	JIANG Shihao

Cite this article:

WU Hefeng,WANG Guowei,WAN Zaojun等. Infrared target detection model for distribution equipment based on improved YOLOv8s[J]. Electrical Engineering, 2024, 25(3): 18-23.

URL:

http://dqjs.cesmedia.cn/EN/Y2024/V25/I3/18

[1] 夏得青, 向星宇, 李宽龙, 等. 农村配电网低电压治理研究进展[J]. 电气技术, 2023, 24(6): 1-5.
[2] 林华梁, 彭松. 配电终端绝缘性能自动测试系统的研究与应用[J]. 电气技术, 2023, 24(5): 65-70.
[3] 董章, 李思尧, 陈雅旎, 等. 计及罕见变量的配电电缆线路故障风险预警方法[J]. 电气技术, 2023, 24(5): 35-40.
[4] 杨帆, 王梦珺, 谭天, 等. 基于目标像素宽度识别的电力设备红外成像单目测距改进算法[J]. 电工技术学报, 2023, 38(8): 2244-2254.
[5] 郑含博, 李金恒, 刘洋, 等. 基于改进YOLOv3的电力设备红外目标检测模型[J]. 电工技术学报, 2021, 36(7): 1389-1398.
[6] 俞峰. 基于深度学习的配电设备视觉识别技术研究[D]. 杭州: 浙江大学, 2021.
[7] 陈明, 赵连飞, 苑立民, 等. 基于特征选择YOLOv3网络的红外图像绝缘子检测方法[J]. 红外与激光工程, 2020, 49(增刊2): 262-267.
[8] 杨波, 曹雪虹, 焦良葆, 等. 改进实时目标检测算法的电力巡检鸟巢检测[J]. 电气技术, 2020, 21(5): 21-27, 32.
[9] 马丽萍, 贠鑫, 马文哲, 等. 基于改进YOLOv3模型的道路车辆多目标检测方法[J]. 西安工程大学学报, 2021, 35(5): 64-73.
[10] 李烨, 顾晨峰. 基于注意力机制的多尺度小目标交通标志检测[J]. 小型微型计算机系统, 2022, 43(2): 381-386.
[11] 李瑞生, 张彦龙, 翟登辉, 等. 基于改进SSD的输电线路销钉缺陷检测[J]. 高电压技术, 2021, 47(11): 3795-3802.
[12] 单亚锋, 赵天宇, 付昱, 等. 基于4层 R-CNN的输电线路多目标检测[J]. 辽宁工程技术大学学报(自然科学版), 2022, 41(3): 270-276.
[13] 阮顺领, 阮炎康, 卢才武, 等. 基于红外图像的矿石传送带托辊异常检测[J]. 黄金科学技术, 2023, 31(1): 123-132.
[14] 臧国强, 刘晓莉, 徐颖菲, 等. 深度学习在电力设备缺陷识别中的应用进展[J]. 电气技术, 2022, 23(6): 1-7.
[15] 徐正军, 张强, 许亮. 一种基于改进YOLOv5s-Ghost网络的交通标志识别方法[J]. 光电子·激光, 2023, 34(1): 52-61.
[16] 熊恩杰, 张荣芬, 刘宇红, 等. 面向交通标志的Ghost-YOLOv8检测算法[J]. 计算机工程与应用, 2023, 59(20): 200-207.
[17] 黄子杰, 欧阳, 江德港, 等. 面向牵引座焊缝表面质量检测的轻量型深度学习算法[J]. 计算机应用, 2024, 44(3): 983-988.