检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:李奕炜 骆立实 赵波 何红亮 李维江 武建松 王晋元 周可新 LI Yiwei;LUO Lishi;ZHAO Bo;HE Hongliang;LI Weijiang;WU Jiansong;WANG Jinyuan;ZHOU Kexin(State Grid Jibei Electric Power Co.,Ltd.Ultra High Voltage Branch,Beijing 102488,China)
机构地区:[1]国网冀北电力有限公司超高压分公司,北京102488
出 处:《电信科学》2025年第3期179-189,共11页Telecommunications Science
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。With the rapid development of smart grid construction in China at present,there is a higher demand for di versified and intelligent video monitoring systems in substations.A multi-target intelligent tracking method for substa tion 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 dis tant 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 tar gets 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:变电站视频监控系统 YOLO v8算法 多目标智能跟踪 注意力机制 卡尔曼滤波器
分 类 号:TN948.6[电子电信—信号与信息处理]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.15