基于灰度梯度联合二值图的抗干扰指针仪表自动识读方法  

Automatic Recognition Research of Pointer Meter Based on Contour Features and Line Detection

作　　者：尹春丽 刘波 滕松 王丹 秦轩 梁庆华[2] 吴甜 蒲廷燕 YIN Chunli;LIU Bo;TENG Song;WANG Dan;QIN Xuan;LIANG Qinghua;WU Tian;PU Tingyan(State Grid Jiangsu Electric Power Co.,Xuzhou Branch,Xuzhou Jiangsu 221000,China;School of Mechanical Engineering,Shanghai Jiao Tong University,Shanghai 200240,China;Beijing Ruiying Zhituo Technology Development Co.,Ltd.,Beijing 100032,China)

机构地区：[1]国网江苏省电力有限公司徐州供电公司,江苏徐州221000 [2]上海交通大学机械与动力工程学院,上海20020 [3]北京瑞盈智拓科技发展有限公司,北京100032

出　　处：《机械设计与研究》2019年第6期43-47,共5页Machine Design And Research

基　　金：国网总部资助科技项目:“基于人工智能的多任务协同配电站值守作业机器人研发”。

摘　　要：无人值守机器人在智能配电房进行设备状态检测过程中,需对配电房内的各类指针式仪表进行自动化识别判读。对于方型指针式仪表检测过程中出现的大角度倾斜、阴影与反光干扰,提出一种基于灰度梯度比值阵与联合二值图的抗干扰指针识别算法。在表盘定位过程中,提出基于灰度直方图峰值检测与灰度梯度比值阵相结合的方法,有效消除了边框阴影的干扰,实现四条边框方向的定位;在指针识别过程中,提出基于联合二值图的方法,有效增强了表盘中的指针信息,并通过Hough直线检测与线段聚类,最终进行倾斜校正从而获取指针角度。利用C++语言与OpenCV视觉库在计算机中进行算法实现与验证,结果表明,该算法在强干扰条件下仍表现出较高的鲁棒4生和精度,具有较高的应用价值。In the process of equipment state detection,the unattended robots need to automatically recognize and interpret pointer meters in the power distribution room.In view of the shortcomings of square pointer meter recognition and the interference factors of image acquisition environment,an anti一interference recognition algorithm based on gradient gray ratio matrix and combined binary image is proposed.In the process of meter frame positioning,the gradient gray ratio matrix and peak detection method of gray histogram is proposed to position four frames precisely.In the pointer recognition process,the concept of the gray-gradient combined binary image is proposed,and the Hought Transform and line segment feature clustering method is used to recognize the pointer.Finally,the tilt correction model based on perspective transformation is used to calculate the pointer angle.After the algorithm implementation and experimental verification with OpenCV and C++,the result shows that the algorithm has high accuracy,stability and anti-interference ability,which meets the accuracy requirements and has high application value.

关 键 词：方形指针式仪表 灰度梯度比值阵 联合二值图 HOUGH变换 聚类方法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]