摘要
由于传统方法无法实现协同巡检的视频信息智能采集,采集视频图像的模糊度辨识特征量不高,提出了基于机器人和视频监控的变电站多维立体协同巡检技术。利用机器人智能采集变电站巡检的视频信息,对其信息进行边缘轮廓特征检测;在视频图像中提取模糊度辨识特征量,结合空间区域融合滤波跟随识别技术实现视频监控识别;构建可靠性视觉识别模型,实现变电站多维立体协同巡检。仿真结果表明,巡检图像输出准确率达到92%以上,变电站的视觉故障跟踪识别能力较好。
Because the traditional methods can not realize the intelligent collection of video information in collaborative inspection,the fuzzy identification characteristics of video images are not high,and the multi-dimensional and three-dimensional cooperative inspection technology of substation based on robot and video monitoring is proposed.The video information of substation inspection is collected by robot intelligently,and the edge contour feature of the information is detected.The feature quantity of fuzzy degree identification is extracted from the video image,and the video monitoring recognition is realized by combining the spatial region fusion filter following recognition technology.The simulation results show that the output accuracy of inspection image is more than 92%,and the visual fault tracking and recognition ability of substation is better.
作者
曾林
高彦波
王胜涛
徐燕宁
朱俊飞
ZENG Lin;GAO Yan-bo;WANG Sheng-tao;XU Yan-ning;ZHU Jun-fei(State Grid Taizhou Power Supply Company,Taizhou 318000,China;State Grid Zhejiang Taizhou Huangyan Power Supply Co.,Ltd.,Taizhou 318020,China;State Grid Zhejiang Yuhuan Power Supply Co.,Ltd.,Taizhou 318000,China)
出处
《自动化与仪表》
2021年第2期105-108,共4页
Automation & Instrumentation
关键词
变电站
多维立体
协同巡检
机器人
视频监控
substation
multidimensional stereo
collaborative patrol inspection
robot
video surveillance