摘要
端子作为线束生产的重要组件,利用视觉成像检测其姿态是汽车智能制造领域的研究课题之一。线束端子旋转角度自动检测设备通常利用机器视觉获取端子的姿态,提出一种线束端子角度姿态的视觉检测方法,利用电机将端子匀速旋转90°,并在旋转过程中连续采集图像,获得端子的旋转图像序列;根据端子旋转过程的成像特点,找到金属面正对的图像帧,并提取ROI图像;以该ROI图像为对象,利用端子模板库进行匹配,判断得到该金属面所属类别,从而计算出端子需要旋转的角度传输给电机。大量实验结果表明,所提出的方法可以有效地识别端子的角度姿态,并且快速准确地计算旋转角度,可以达到工业智能制造的要求。
As an important component of harness production,it is one of the research topics in the field of automobile intelligent manufacturing to detect the attitude of terminals by using visual imaging.The machine vision is usually used to obtain the attitude of the terminal in the automatic terminal rotation-angle detection equipment.In this paper,a visual detection method for the angle attitude of harness terminal is proposed,which uses the motor to rotate the terminal at a constant speed of 90 degrees,and continuously collects images during the rotation process to obtain the rotation image sequence of the terminal.According to the imaging characteristics of the terminal in the rotation process,we can find the image of the metal face and extract ROI image.Taking the ROI image as the object,the terminal template library is used to match and determine the category of the metal surface,so as to calculate the rotation angle of the terminal and transmit it to the motor.A large number of experimental results show that the proposed method can effectively identify the angle attitude of the terminal,and calculate the rotation angle quickly and accurately,which can meet the requirements of industrial intelligent manufacturing.
作者
王雨青
陈小林
余毅
Wang Yuqing;Chen Xiaolin;Yu Yi(Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China;Jihua Laboratory,Foshan 528234,China)
出处
《国外电子测量技术》
2020年第3期80-85,共6页
Foreign Electronic Measurement Technology
关键词
视觉检测
红色LED光源
分类器
模板匹配
端子姿态
目标识别
visual detection
red LED light source
classifier
template matching
terminal attitude
target recognition