基于灰度相关匹配的工业分拣系统实现  

Realization of Industrial Sorting System Based on Gray Correlation Matching

作　　者：曹兰 CAO Lan(Zhangzhou Institute of Technology,Zhangzhou,Fujian 363000,China)

机构地区：[1]漳州职业技术学院电子信息学院,福建漳州363000

出　　处：《龙岩学院学报》2022年第2期39-45,共7页Journal of Longyan University

基　　金：福建省中青年教师教育科研项目(JAT191419,JAT210844);漳州职业技术学院校级课题(ZZY2021B042)。

摘　　要：为解决使用传统示教或离线编程方式的工业机器人无法满足实时数据采集要求,以爱普生工业机器人与2D相机为硬件基础,搭建了一个基于机器视觉的自动分拣系统。先采用4点标定版在Halcon上实现手眼标定,再采用基于灰度相关的目标匹配算法,并用多阀值模板匹配和图像金字塔降低算法复杂度,实现对分拣对象的实时数据采集和快速识别分拣。实验结果表明:搭建的智能分拣系统运行稳定,满足对传送带上的物体进行自动分拣的精度要求,具有一定的工业应用价值。In order to solve the problem that industrial robots using traditional teaching or offline programming methods cannot meet the requirements of real-time data collection,on the hardware platform composed of 2D cameras and the robots of EPSON,an automatic sorting system based on machine vision is built.The system first uses a 4-point calibration version to achieve hand-eye calibration on Halcon,and then uses a gray-level correlation target matching algorithm and uses multi-threshold template matching and image pyramids to reduce the complexity of the algorithm and achieve real-time data collection and fast speed of sorting and recognizing objects.The experimental results show that the intelligent sorting system built is stable,meets the accuracy requirements for automatic sorting of objects on the conveyor belt,and has certain industrial application value.

关 键 词：灰度相关 自动分拣 阀值匹配 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]