基于图像识别技术的变电站视频监控系统设计  

Design of substation video surveillance system based on image recognition technology

作　　者：高梅鹃 刘达 庄建斌 李云瑞 GAO Meijuan;LIU Da;ZHUANG Jianbin;LI Yunrui(Jiaxing Hengchuang Electric Power Design&Research Institute Co.,Ltd.,Jiaxing 314000,China)

机构地区：[1]嘉兴恒创电力设计研究院有限公司,浙江嘉兴314000

出　　处：《电子设计工程》2021年第22期175-179,共5页Electronic Design Engineering

基　　金：嘉兴恒创电力设计研究院有限公司资助项目(2019-ZZKJ-001)。

摘　　要：为实现对变电站主控节点的连续性监测,生成完整的变电站监控视频,文中设计了基于图像识别技术的变电站视频监控系统。以C/S体系作为底层应用架构,连接ActiveX控件与周界监控主机,实现对监控系统硬件执行环境的搭建;通过分类监控图像的方式获取准确的视频图像灰度化处理结果,再将数据信息转存至数据库表结构中,实现对系统软件执行环境的搭建。在此基础上,结合相关硬件设备完成对变电站视频监控系统的整合设计。对比实验结果表明,与传统监控系统相比,该文系统对连续性视频图像的识别准确度更高,且监控指令的执行耗时更短,符合连续性监测变电站主控节点的实际应用需求。In order to realize continuous monitoring of substation master control node and generate complete substation monitoring video,a substation video monitoring system based on image recognition technology is designed.C/S system is taken as the underlying application architecture to connect ActiveX control with the perimeter monitoring host to build the hardware execution environment of the monitoring system.Accurate grayscale processing results of video images are obtained by classifying monitoring images,and then the data information is transferred to the database table structure to achieve the establishment of the system software execution environment.On this basis,combined with the relevant hardware equipment to complete the integrated design of the substation video monitoring system.Compared with the traditional monitoring system,the experimental results show that the recognition accuracy of continuous video images in this system is higher,and the execution time of monitoring instructions is shorter,which meets the practical application requirements of continuous monitoring substation master control node.

关 键 词：图像识别技术 C/S体系 ACTIVEX控件 周界主机 图像灰度化 数据库表 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]