基于视觉技术的分类叠衣与存衣系统的设计  

Design of Classification Folding and Storage System Based on Visual Technology

作　　者：刘长红[1] 江沐鸿 谭泰臻 林韦任 刘晓初[1] Liu Changhong;Jiang Muhong;Tan Taizhen;Lin Weiren;Liu Xiaochu(School of Mechanical and Electrical Engineering,Guangzhou University,Guangzhou 510006,China)

机构地区：[1]广州大学机械与电气工程学院,广州510006

出　　处：《机电工程技术》2025年第2期106-110,共5页Mechanical & Electrical Engineering Technology

基　　金：广东省科技创新战略专项资金(“攀登计划”专项资金)资助立项项目(pdjh2021b0392);广东省科技计划项目(2020A1414050067);广州市科技计划项目(202102010392)。

摘　　要：针对酒店、医院等公共服务场所缺少合适的自动化叠衣设备,以及当前繁琐叠衣过程挤占人们日常业余时间的问题,结合目前国内外的叠衣产品发展现状与现有技术,设计了一套基于视觉技术的分类叠衣与存衣系统,通过预折叠机构、夹取移动机构、折叠机构、分类机构的一系列机械系统与基于视觉处理与卷积神经网络的衣服自动识别技术,对不同种类的衣物实现从进入到分类的有效折叠存放过程。通过实验测试表明:设计的系统对不同种类的衣物处理情况良好,从开始到分类存放的单件处理总时间约21 s,折叠后衣物平整,折叠效果良好,具有很高的使用价值,是当代工业自动化和数字化时代的综合产物。With the problem of the lack of suitable automatic clothing folding systems in public service places such as hotels and hospitals,as well as the current tedious folding process that squeezes people′s daily leisure time,a set of visual technology-based classification and networking clothing storage system is designed.Which utilizes a series of mechanical systems,including pre-folding modules,grasping and moving modules,folding modules,and classification modules,as well as clothing automatic recognition technology based on visual processing and convolutional neural networks,to effectively fold and store different types of clothing from entry to classification.The experimental results show that the system performs well in processing different types of clothing.The total processing time from start-up to classification storage is about 21 s,and the clothing is well folded,flat and folded well.The system has high use value,it is a comprehensive product of contemporary industrial automation and digital age.

关 键 词：衣物 分类折叠 卷积神经网络 机器视觉 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]