YOLOv5神经网络的智能巡检仪表动态追踪读取算法  

Dynamic Tracking and Reading Algorithm of Intelligent Patrol Instrument based on YOLOv5 Neural Network

作　　者：吴耀华 柴立平[1] 朱利凯[2] 李跃 WU Yao-hua;CHAI Li-ping;ZHU Li-kai;LI Yue(School of Mechanical Engineering,Hefei University of Technology,Hefei 230009,Anhui,China;Hefei Institutes of Physical Science,Chinese Academy of Sciences,Hefei 230031,Anhui,China)

机构地区：[1]合肥工业大学机械工程学院,安徽合肥230009 [2]中国科学院合肥物质科学研究院,安徽合肥230031

出　　处：《机械研究与应用》2025年第2期55-62,共8页Mechanical Research & Application

摘　　要：通过巡检机器人进行仪表数字化读取是当前发展的潮流。然而,现有研究主要针对采集后的仪表图像进行表盘读数,缺乏仪表图像的智能采集过程,导致采集图像流程复杂、图像清晰度低和质量差等问题,因此提高采集设备在巡检作业过程中的有效配合度,开展相关算法研究成为当前重点。尤其在石化场景下的巡检作业中,需要一种更为柔性化的巡检方式。文章提出了一种基于YOLOv5神经网络的仪表检测和偏角补偿的追踪方法,该方法通过目标检测来获取目标位置信息并计算偏角,研究了追踪块方式下的目标追踪算法,使表盘以合适的比例置于整体图像的中央。实验验证表明,YOLOv5神经网络能够较好地完成仪表定位工作,同时使得到的目标位置偏角误差小于画面比例的5%,能够准确完成仪表目标追踪工作,并获取理想的待识别表盘。该研究对于提高巡检机器人工作可靠性,减少后期维护成本,推动无人化巡检有一定工程应用价值。The digital reading of instrument by inspection robot is the current trend of development;the existing research mainly focuses on the dials reading of the collected instrument images,and the lack of intelligent acquisition process of instrument images,resulting in complex image acquisition process,low image definition and poor image quality.Thus to improve the effective coordination of acquisition equipment in the inspection operation and conduct the research of relevant algorithms has become the current focus,especially in the petrochemical scenario,the inspection operations require a more flexible inspection method.This paper proposes a tracing method for instrument detection which based on YOLOv5 neural network and deviation angle compensation.The target position information is obtained by the method of target detection,and the deviation angle is calculated.The target tracking algorithm in the tracking module is studied so that the dial is placed in the center of the overall image with an appropriate proportion.It has been verified that YOLOv5 neural network can better complete the instrument positioning work,and the obtained deviation error of the target position is less than 5%of the screen proportion.It can effectively complete the instrument target tracking work and obtain the ideal dial to be identified.This research has certain engineering application value for improving the working reliability of inspection robots,reducing the maintenance cost in the later stage,and promoting the unmanned inspection.

关 键 词：目标追踪 YOLOv5 偏角补偿 巡检机器人 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]