基于双目视觉的L型板几何参数测量研究  

Research on Geometric Parameter Measurement of L-shaped Plate based on Binocular Vision

作　　者：周海宇 刘兴德[2] 蔚芳鑫 卢添烨 刁建超 ZHOU Haiyu;LIU Xingde;YU Fangxin;LU Tianye;DIAO Jianchao(School of Information and Control Engineering,Jilin Institute of Chemical Technology,Jilin 132022,China;School of Mechanical and Electrical Engineering,Jilin Institute of Chemical Technology,Jilin 132022,China)

机构地区：[1]吉林化工学院信息与控制工程学院,吉林吉林132022 [2]吉林化工学院机电工程学院,吉林吉林132022

出　　处：《吉林化工学院学报》2022年第3期83-87,共5页Journal of Jilin Institute of Chemical Technology

基　　金：吉林省科学技术厅项目(20190302080GX);吉林市科学技术局项目(201750209)。

摘　　要：机器视觉在智能制造领域应用越来越广.文章提出一种基于双目视觉模型对L型板几何参数测量的方法.首先对双目相机标定,获取内外参数,然后对比边缘检测算法,采用Sobel算法对L型板图像进行处理,最后基于三角测量原理提取工件特征点的三维坐标,计算出L型板的几何参数.实验表明,该算法测量误差低,能够满足实际需求.Machine vision enjoys increasingly wide application in intelligent manufacturing.This paper introduced a method for measurement of geometric parameters of L-shaped plate based on binocular vision model.First,the intrinsic and extrinsic parameters were obtained after calibration of the binocular camera;then,compared with the edge detection algorithm,the image of the L-shaped plate was processed with Sobel algorithm;in the end,based on triangulation theory,the three-dimensional coordinates of the feature points of the workpiece were extracted to work of the geometric parameters of the L-shaped plate.According to the experiment,the algorithm was of small measurement error and was able to meet the actual needs.

关 键 词：双目视觉 相机标定 SOBEL算法 几何参数测量 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]