基于双目视觉零件特征测量技术的研究  

Research on Key Technology of Part Feature Measurement Based on Binocular Vision

作　　者：胡炜[1] 李长春[1] HU Wei;LI Changchun

机构地区：[1]苏州工业职业技术学院

出　　处：《计量与测试技术》2023年第2期31-34,共4页Metrology & Measurement Technique

基　　金：江苏省优秀科技创新团队、学院优秀科技创新团队(项目编号:2020kytd01);服务企业技术技能平台(项目编号:2020kypt01);学院横向课题(项目编号:SIITHT2021004215)。

摘　　要：通过eye on hand模式,对上下料机器人配置双目视觉系统,将获得的图像进行处理后,判断工件的尺寸、位姿等信息,为上下料操作提供数据支持,使其能准确抓取工件。本文根据双目测量的理论基础,利用Harris角点算法获取零件的角点,对左右相机获取的图像进行区域匹配操作,进而获得工件的特征信息。最后,利用MATLAB对工件进行特征的提取和测量实验,为后续的研究工作提供了基础。Through the eye on hand mode,binocular vision system is configured for the loading and unloading robot.After processing the acquired images,the size and pose of the workpiece are judged to provide data support for the loading and unloading operation,so that it can accurately grasp the workpiece.In this paper,according to the theoretical basis of binocular measurement,the Harris corner algorithm is used to obtain the corners of parts,and the region matching operation is carried out on the images obtained by the left and right cameras,so as to obtain the feature information of the workpiece.Finally,the feature extraction and measurement experiment of the workpiece are carried out by MATLAB,which provides a foundation for the subsequent research work.

关 键 词：双目视觉 上下料机器人 测量 特征匹配 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]