基于机器视觉的建筑垃圾自动分类系统研究  

Research on Automatic Classification System of Building Waste Based on Machine Vision

作　　者：郑龙海 袁祖强[1] 殷晨波[1] 陈曦 刘久晨 ZHENG Long-hai;YUAN Zu-qiang;YIN Chen-bo;CHEN Xi;LIU Jiu-chen(School of Mechanical and Power Engineering,Nanjing Tech University,Nanjing 211816,China)

机构地区：[1]南京工业大学机械与动力工程学院

出　　处：《机械工程与自动化》2019年第6期16-18,共3页Mechanical Engineering & Automation

基　　金：江苏省科技计划前瞻性联合研究项目(BY2015005-15)

摘　　要：针对现有建筑垃圾分类不清,且自动化程度不高的情况,提出了一种基于机器视觉与称重技术相结合的分类方法,即将建筑垃圾中的木材和碎砖石进行标识分类。该方法首先利用带传动系统中的称重传感器测量经过物体的质量,并通过图像采集装置获取物体的左、右视图和俯视图,根据明暗信息恢复形状算法(SFS算法)获得物体表面高度,求取目标物体体积;然后把对应物体的质量与体积进行编号存储,经SVM分类学习后,能够有效地将建筑垃圾中常见的木头和砖石进行自动分类并回收利用。Aiming at the unclear classification of existing construction waste and the low degree of automation,a classification method based on the combination of machine vision and weighing technology is proposed,which is to classify wood and brick in construction waste.Firstly,the weighing sensor in the belt drive system is used to measure the mass of the object,and the image acquisition device is notified to obtain the views(left,right and top)of the object in real time.According to the shading information recovery shape algorithm(SFS algorithm),the surface height of the object is obtained,and the target object volume is obtained.Then the mass and volume of the corresponding object are numbered and stored.After SVM classification learning,the wood and masonry commonly found in construction waste can be automatically classified and recycled.

关 键 词：机器视觉 SFS算法 SVM分类器 垃圾自动分类 建筑垃圾 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TP242.6[自动化与计算机技术—控制科学与工程]