一种适用于智能变电站巡检机器人的双针仪表读数的识别算法  

Double Pointers Meter Recognition Algorithm for Equipment Inspection Robot

作　　者：房桦 蒋涛 李红玉 罗浩 李健 杨国庆 

机构地区：[1]山东鲁能智能技术有限公司,山东济南250002 [2]长治供电局,山西长治046000

出　　处：《山东电力技术》2013年第3期9-13,69,共6页Shandong Electric Power

摘　　要：提出一种适合智能变电站巡检机器人室外工作环境的对变电站双指针式仪表设备读数的识别算法。首先针对双针仪表设备图像,进行设备模板化处理,并在模板库中建立仪表的min刻度和max刻度的位置信息。对于机器人实时采集的仪表图像,先要在后台服务中调取相应采集位置设备的模板图,利用尺度不变特征变换(SIFT)算法,在输入图像中匹配提取仪表表盘区域子图像。而后除去上方指针在表盘中的阴影降低指针误识别率,再对表盘子图像进行二值化、仪表指针骨干化处理,利用快速霍夫变换(Fast Hough Transform)检测两条指针直线去除噪音干扰,定位指针精确位置和指向角度,完成指针读数。此算法经过国内某500 kV智能变电站巡检机器人实地测试,各种仪表综合识别率超过95%,对仪表的读数具有高精度高鲁棒性,完全满足该智能变电站推进无人值守的仪表设备读数自动检测识别的要求。A double pointers meter recognition algorithm is proposed which is adapted to suit the equipment inspection robot works outdoor in the smart substation. First, the template images are made for the meter and the ＂min＂ and ＂max＂ values are illustrated for each template image. SIFT method is utilized to match with the template image for detecting the meter device region from the real-time image captured by the robot. And then, the shadows removing procedure is necessary to improve the accuracy. A fast Hough transform method is proposed to detect the line in the preprocessed image as the pointer of the meter. Comparing the angle with the ＂min＂ or ＂max＂ value the result of the meter can be recognized. This algorithm has been applied in one 500 kV smart substation in China. Experimental results of various meters have shown good performance, which proves that the proposed method is both effective and accurate.

关 键 词：智能变电站 巡检机器人 双针仪表识别 SIFT配准 除阴影 快速HOUGH变换 

分 类 号：TM163[电气工程—电工理论与新技术] TP242.2[自动化与计算机技术—检测技术与自动化装置]