摘要
为了满足变电站巡检机器人对现场表计指针的智能识读要求,文中提出一种基于扩展扫描区域的现场表计指针识别方法。通过改进的SIFT算法进行图像匹配并求出单应矩阵,利用单应矩阵将在模板图像上标定的刻度弧线映射到待测图像上,通过扩展扫描区域,依据检测曲线路径上像素点的灰度值和确定指针位置并计算读数。文中对变电站现场的五种仪表,共计500张图片进行了测试。实验结果表明,文中所提算法简单实用、稳定且识别精度高,可以对多种不同的仪表进行识别,适用性强,在变电站多类指针表计识别中具有较好的应用前景。
In order to satisfy the intelligent identification requirements of the substation inspection robot for the field meter pointer,a pointer recognition method based on the extended scanning area has been proposed in this paper.Image matching is performed by the improved SIFT algorithm and the homography matrix could be obtained.The scale arc calibrated on the template image is mapped onto the test image by the homography matrix.Expanding the scanning area,the sum of the gray values of the pixel on the path of the detection line is determined.It determines the position of the pointer and calculates the reading.A total of 500 pictures of five meters have been tested in this paper.The experimental results show that the proposed algorithm is simple,practical,stable and has high recognition accuracy.It can identify many different meters and has strong applicability.It has good application prospect in the identification of multi-class pointer meter in substation.
作者
黄炎
李文胜
李英杰
麦晓明
董娜
Huang Yan;Li Wensheng;Li Yingjie;Mai Xiaoming;Dong Na(Electric Power Research Institute of Guangdong Power Grid Co.,Ltd.,Guangzhou 510080,China.;School of Automation,Tianjin University,Tianjin 300072,China)
出处
《电测与仪表》
北大核心
2020年第16期141-146,共6页
Electrical Measurement & Instrumentation
关键词
特征匹配
单应矩阵
扩展扫描区域
指针识别
feature matching
homography matrix
extended scanning area
pointer recognition
作者简介
黄炎(1991-),男,汉族,工程师,工程硕士,研究方向为电力机器人技术研究与应用,图像智能识别,Email:huangyan_dky@163.com;李文胜(1984-),男,汉族,高级工程师,工学博士,研究方向为电力机器人技术研究与应用、图像智能识别;李英杰(1995-),男,汉族,工学硕士,研究方向为图像智能识别、机器学习;麦晓明(1986-),男,汉族,高级工程师,工学硕士,研究方向为电力机器人技术研究与应用、图像智能识别;董娜(1983-),女,汉族,副教授,工学博士,研究方向为图像智能识别、非线性控制算法,深度学习。
