面向带电作业的跌落保险装置识别定位技术  

Fall Insurance Identification and Positioning Technology for Live-line Work

作　　者：段宜 车玉奎 文虎标 杨海贤 张伟军[2] DUAN Yi;CHE Yukui;WEN Hubiao;YANG Haixian;ZHANG Weijun(Malong Power Supply Bureau of Yunnan Power Grid Co.,Ltd.,Qujing Yunnan 655000,China;School of Mechanical and Engineering,Shanghai Jiao Tong University,Shanghai 200240,China)

机构地区：[1]云南电网有限责任公司马龙供电局,云南曲靖655000 [2]上海交通大学机械与动力工程学院,上海200240

出　　处：《机械设计与研究》2024年第6期58-63,共6页Machine Design And Research

摘　　要：使用机器人进行带电作业,需要对作业目标的位置和姿态进行精确的识别和定位。在带电作业环境中,跌落保险的识别需要解决背景、强光干扰问题,并要求较高的可靠性和实时性。针对带电作业中跌落保险的识别和定位问题开展了研究,提出了一种基于形状匹配和交互式训练的识别方法。文中设计了面向形状匹配的加速算法,提高了识别定位的实时性。针对可靠性要求,提出了分块匹配的方法,减少了背景干扰的影响,提高了识别效果的可靠性。通过室内外实验,验证了该算法的有效性和可靠性。When robots are used in live work,it is necessary to identify and locate the position and altitude of the target accurately.In live-line working environment,the identification of fall insurance needs to solve the problems of background and glare interference,and requires high reliability and real-time identification.In this paper,a recognition method based on shape matching and interactive training is proposed for the identification and locating of fall insurance in live operation,and an acceleration algorithm for shape matching is designed to improve the real-time recognition and positioning.Aiming at the reliability requirements,a block matching method is proposed,which reduces the influence of background interference and improves the reliability of recognition.Through indoor and outdoor experiments,the effectiveness and reliability of the proposed algorithm are verified.

关 键 词：带电作业 跌落保险 形状匹配 交互式训练 

分 类 号：TP242.3[自动化与计算机技术—检测技术与自动化装置]