基于YOLO v8算法的变电站视频监控多目标智能跟踪方法

李奕炜; 骆立实; 赵波; 何红亮; 李维江; 武建松; 王晋元; 周可新

doi:10.11959/j.issn.1000-0801.2025025

您当前的位置：

首页 >

文章列表页 >

基于YOLO v8算法的变电站视频监控多目标智能跟踪方法

工程与应用 | 更新时间：2025-04-24

- 基于YOLO v8算法的变电站视频监控多目标智能跟踪方法
- Multi-target intelligent tracking method for substation video surveillance based on YOLO v8 algorithm
- 电信科学 2025年41卷第3期页码：179-189
- 作者机构：
  
  国网冀北电力有限公司超高压分公司，北京 102488
- 作者简介：
  
  [ "李奕炜（1992- ），女，国网冀北电力有限公司超高压分公司工程师，主要研究方向为输变电运检。" ]
  骆立实（1977- ），男，国网冀北电力有限公司超高压分公司高级工程师，主要研究方向为输变电运检。
  赵波（1980- ），男，国网冀北电力有限公司超高压分公司高级工程师，主要研究方向为输变电运检。
  何红亮（1985- ），男，现就职于国网冀北电力有限公司超高压分公司，主要研究方向为输变电运检。
  李维江（1989- ），男，现就职于国网冀北电力有限公司超高压分公司，主要研究方向为输变电运检。
  武建松（1989- ），男，现就职于国网冀北电力有限公司超高压分公司，主要研究方向为输变电运检。
  王晋元（1985- ），男，现就职于国网冀北电力有限公司超高压分公司，主要研究方向为输变电运检。
  周可新（1986- ），女，现就职于国网冀北电力有限公司超高压分公司，主要研究方向为输变电运检。
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2025025
  中图分类号： TN948.6
- 收稿日期：2024-07-15，
  
  修回日期：2024-10-15，
  
  纸质出版日期：2025-03-20
- 稿件说明：
移动端阅览
李奕炜,骆立实,赵波等.基于YOLO v8算法的变电站视频监控多目标智能跟踪方法[J].电信科学,2025,41(03):179-189.

LI Yiwei,LUO Lishi,ZHAO Bo,et al.Multi-target intelligent tracking method for substation video surveillance based on YOLO v8 algorithm[J].Telecommunications Science,2025,41(03):179-189.
李奕炜,骆立实,赵波等.基于YOLO v8算法的变电站视频监控多目标智能跟踪方法[J].电信科学,2025,41(03):179-189. DOI： 10.11959/j.issn.1000-0801.2025025.

LI Yiwei,LUO Lishi,ZHAO Bo,et al.Multi-target intelligent tracking method for substation video surveillance based on YOLO v8 algorithm[J].Telecommunications Science,2025,41(03):179-189. DOI： 10.11959/j.issn.1000-0801.2025025.

摘要

现阶段我国智能电网建设迅速发展，对变电站视频监控系统提出了更高的多样化、智能化需求。针对现有变电站视频监控摄像头对人员、车辆、异常入侵识别精度不足的问题，提出了一种基于YOLO v8算法的变电站视频监控多目标智能跟踪方法。首先，利用YOLO v8算法对变电站目标进行监测，通过采样算法加大感受野进而提升数据特征融合能力，采用注意力机制识别远处微小目标；然后，基于卡尔曼滤波器和变电站摄像头运动防抖，将YOLO v8监测到的信息输入BoTSORT 算法，完成多场景多目标下的变电站视频监控目标智能跟踪；最后，实验验证表明，该方法相比于YOLO v5、YOLO v7算法，目标识别平均精度均值分别提升了9.73个百分点、5.28个百分点，目标跟踪精度分别提升了12.34个百分点、8.41个百分点，提升了变电站视频监控系统智能化水平。

Abstract

With the rapid development of smart grid construction in China at present

there is a higher demand for diversified and intelligent video monitoring systems in substations. A multi-target intelligent tracking method for substation video surveillance based on YOLO v8 algorithm was proposed to address the issue of insufficient accuracy in identifying personnel

vehicles

and abnormal intrusions using existing substation video surveillance cameras. Firstly

the YOLO v8 algorithm was used to monitor the substation targets

and the sampling algorithm was used to increase the receptive field and improve the data feature fusion ability. The attention mechanism was used to identify small distant targets. Then

based on Kalman filter and substation camera motion stabilization

the information monitored by YOLO v8 was input into the BoTSORT algorithm to achieve intelligent tracking of substation video monitoring targets in multiple scenes and targets. Finally

experimental verification shows that compared to the YOLO v5 and YOLO v7 algorithms

the average accuracy of target recognition proposed has been improved by 9.73 percent and 5.28 percent

respectively

and the accuracy of target tracking has been improved by 12.34 percent and 8.41 percent

respectively. This has improved the intelligence level of the substation video monitoring system.

关键词

Keywords

references

杨至元 , 张仕鹏 , 孙浩 , 等 . 基于Cyber-net与学习算法的变电站网络威胁风险评估 [J ] . 电力系统自动化 , 2020 , 44 ( 24 ): 19 - 27 .

YANG Z Y , ZHANG S P , SUN H , et al . Risk estimation of cyber threat to substation based on Cyber-net and learning algorithm [J ] . Automation of Electric Power Systems , 2020 , 44 ( 24 ): 19 - 27 .

赵海文 , 齐恒佳 , 王旭之 , 等 . 基于机器学习的人机协调操作意图感知与控制方法研究 [J ] . 机床与液压 , 2019 , 47 ( 10 ): 147 - 150 .

ZHAO H W , QI H J , WANG X Z , et al . Research on the perception and control method of human robot cooperation based on machine learning [J ] . Machine Tool & Hydraulics , 2019 , 47 ( 10 ): 147 - 150 .

蔡正梓 , 程海兴 , 陈茜 , 等 . 基于PSO-SVM的变电站视频监控火灾识别算法 [J ] . 自动化与仪表 , 2022 , 37 ( 7 ): 58 - 62, 67 .

CAI Z Z , CHENG H X , CHEN Q , et al . Substation video surveillance fire recognition algorithm based on PSO-SVM [J ] . Automation & Instrumentation , 2022 , 37 ( 7 ): 58 - 62, 67 .

刘世森 . 基于UWB的矿井人员精准定位技术 [J ] . 煤矿安全 , 2019 , 50 ( 6 ): 118 - 120 .

LIU S S . Accurate positioning technology for mine workers based on UWB [J ] . Safety in Coal Mines , 2019 , 50 ( 6 ): 118 - 120 .

董云峰 , 刘强 . 基于UWB的化工厂人员定位系统设计 [J ] . 智能物联技术 , 2019 , 2 ( 3 ): 42 - 48 .

DONG Y F , LIU Q . Design of chemical plant personnel positioning system based on UWB [J ] . Technology of IoT & AI , 2019 , 2 ( 3 ): 42 - 48 .

赵凌 . 地铁站出入通道多摄像机移动目标跟踪研究 [J ] . 重庆理工大学学报(自然科学) , 2019 , 33 ( 5 ): 95 - 101 .

ZHAO L . Study on moving target tracking of multi-camera in subway access channel [J ] . Journal of Chongqing University of Technology (Natural Science) , 2019 , 33 ( 5 ): 95 - 101 .

江鹏宇 , 杨耀权 , 彭蹦 . 一种用于电力监控的行人运动检测与跟踪算法 [J ] . 电力科学与工程 , 2019 , 35 ( 6 ): 31 - 36 .

JIANG P Y , YANG Y Q , PENG B . A pedestrian motion detection and tracking algorithm for electrical power monitoring [J ] . Electric Power Science and Engineering , 2019 , 35 ( 6 ): 31 - 36 .

刘甜甜 , 彭放 , 张婉 , 等 . 基于图像识别技术的变电站视频监控系统设计 [J ] . 中国设备工程 , 2022 ( 18 ): 84 - 86 .

LIU T T , PENG F , ZHANG W , et al . Design of substation video monitoring system based on image recognition technology [J ] . China Plant Engineering , 2022 ( 18 ): 84 - 86 .

刘艳生 , 王雪军 , 张童飞 , 等 . 基于机器学习算法的变电站内视频监控场景异常感知 [J ] . 电工技术 , 2021 ( 21 ): 179 - 181 .

LIU Y S , WANG X J , ZHANG T F , et al . Abnormal perception of video surveillance scenes in substations based on machine learning algorithms [J ] . Electric Engineering , 2021 ( 21 ): 179 - 181 .

陈汐 , 韩译锋 , 闫云凤 , 等 . 目标物智能跟踪与分割融合算法及其在变电站视频监控中的应用 [J ] . 中国电机工程学报 , 2020 , 40 ( 23 ): 7578 - 7587 .

CHEN X , HAN Y F , YAN Y F , et al . A unified algorithm for object tracking and segmentation and its application on intelligent video surveillance for transformer substation [J ] . Proceedings of the CSEE , 2020 , 40 ( 23 ): 7578 - 7587 .

王浩 , 王功臣 , 娄德章 , 等 . 基于AI边缘深度算法视频分析装置的电力场景异常识别技术研究 [J ] . 电力大数据 , 2021 , 24 ( 11 ): 1 - 8 .

WANG H , WANG G C , LOU D Z , et al . Research on power scene abnormal recognition technology based on AI edge depth algorithm video analysis device [J ] . Power Systems and Big Data , 2021 , 24 ( 11 ): 1 - 8 .

LI B , WU W , WANG Q , et al . SiamRPN: evolution of Siamese visual tracking with very deep networks [C ] // Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2019 : 4277 - 4286 .

ZHU Z , WANG Q , LI B , et al . Distractor-aware Siamese networks for visual object tracking [C ] // Proceedings of the Lecture Notes in Computer Science . Cham : Springer International Publishing , 2018 : 103 - 119 .

LI B , YAN J J , WU W , et al . High performance visual tracking with Siamese Region proposal network [C ] // Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE Press , 2018 : 8971 - 8980 .

BERTINETTO L , VALMADRE J , HENRIQUES J F , et al . Fully-convolutional Siamese networks for object tracking [C ] // Proceedings of the Lecture Notes in Computer Science . Cham : Springer International Publishing , 2016 : 850 - 865 .

BHAT G , DANELLJAN M , VAN GOOL L , et al . Learning discriminative model prediction for tracking [C ] // Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE Press , 2019 : 6181 - 6190 .

DANELLJAN M , BHAT G , KHAN F S , et al . ATOM: accurate tracking by overlap maximization [C ] // Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2019 .

WANG R , GAO Z Z , LI Q F , et al . Detection method of cow estrus behavior in natural scenes based on improved YOLO v5 [J ] . Agriculture , 2022 , 12 ( 9 ): 1339 .

王政 , 许兴时 , 华志新 , 等 . 融合YOLO v5n与通道剪枝算法的轻量化奶牛发情行为识别 [J ] . 农业工程学报 , 2022 , 38 ( 23 ): 130 - 140 .

WANG Z , XU X S , HUA Z X , et al . Lightweight recognition for the oestrus behavior of dairy cows combining YOLO v5n and channel pruning [J ] . Transactions of the Chinese Society of Agricultural Engineering , 2022 , 38 ( 23 ): 130 - 140 .

白强 , 高荣华 , 赵春江 , 等 . 基于改进YOLOV5s网络的奶牛多尺度行为识别方法 [J ] . 农业工程学报 , 2022 , 38 ( 12 ): 163 - 172 .

BAI Q , GAO R H , ZHAO C J , et al . Multi-scale behavior recognition method for dairy cows based on improved YOLOV5s network [J ] . Transactions of the Chinese Society of Agricultural Engineering , 2022 , 38 ( 12 ): 163 - 172 .

梁秀英 , 贾学镇 , 何磊 , 等 . 基于YOLO v8n-seg和改进Strongsort的多目标小鼠跟踪方法 [J ] . 农业机械学报 , 2024 , 55 ( 2 ): 295 - 305, 345 .

LIANG X Y , JIA X Z , HE L , et al . Multi-object mice tracking based on YOLO v8n-seg and improved strongsort [J ] . Transactions of the Chinese Society for Agricultural Machinery , 2024 , 55 ( 2 ): 295 - 305, 345 .

AHARON N , ORFAIG R , BOBROVSKY B Z . BoT-SORT: robust associations multi-pedestrian tracking [EB ] . 2022 , arxiv. org/abs/2206.14651v 2

REDMON J , DIVVALA S , GIRSHICK R , et al . You only look once: unified, real-time object detection [C ] // Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2016 : 779 - 788 .

戚玲珑 , 高建瓴 . 基于改进YOLOv7的小目标检测 [J ] . 计算机工程 , 2023 , 49 ( 1 ): 41 - 48 .

QI L L , GAO J L . Small object detection based on improved YOLOv7 [J ] . Computer Engineering , 2023 , 49 ( 1 ): 41 - 48 .

WANG J Q , CHEN K , XU R , et al . CARAFE: content-aware ReAssembly of FEatures [C ] // Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE Press , 2019 : 3007 - 3016 .

ZHU L , WANG X J , KE Z H , et al . BiFormer: vision transformer with bi-level routing attention [C ] // Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2023 : 10323 - 10333 .

DAI X , CHEN Y , XIAO B , et al . Dynamic head: unifyingobjectdetectionheadswithattentions [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE Press , 2021 : 7373 - 7382 .

GEVORGYAN Z . SIoU loss: more powerful learning for bounding box regression [EB ] . 2022 , arxiv. org/abs/2205.12740v 1 .

WOJKE N , BEWLEY A , PAULUS D . Simple online and realtime tracking with a deep association metric [C ] // Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP) . Piscataway : IEEE Press , 2017 : 3645 - 3649 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向协同感知的无人蜂群智能资源调度方案

基于残差注意力密集网络的协作频谱感知方法

GMTBLC：基于深度学习的双模态网络流量分类

基于改进长短期记忆网络的新能源场站网络安全评估方法研究

基于霍克斯过程的动态异质网络表征学习方法