基于SqueezeNet-Tiny的可回收垃圾智能垃圾桶设计及实现  

Design and Implementation of Intelligent Garbage Can for Recyclable Garbage Based on SqueezeNet-Tiny

作　　者：李长江[1] 余海涛 李官星 李玥洋 谭雯文 LI Changjiang;YU Haitao;LI Guanxing;LI Yueyang;TAN Wenwen(School of Mechanical and Power Engineering,Chongqing University of Science and Technology,Chongqing 401331,China;Fengmingshan Middle School,Chongqing 400030,China;Chongqing Vocational Institute of Engineering,Chongqing 402260,China)

机构地区：[1]重庆科技学院机械与动力工程学院,重庆401331 [2]凤鸣山中学,重庆400030 [3]重庆工程职业技术学院,重庆402260

出　　处：《现代信息科技》2022年第17期75-77,共3页Modern Information Technology

摘　　要：文章提出一种对SqueezeNet神经网络改进策略,通过删除第三个Maxpooling层,同时将第一个卷积层的卷积核大小设置成3×3,创建轻量化SqueezeNet-Tiny模型,并在具有复杂背景的可回收垃圾数据集(Recyclable Waste Dataset,简称RW Dataset)上验证了改进的有效性。将SqueezeNet-Tiny迁移到硬件设施,完成了智能分类垃圾桶的设计和制作,识别精度可达94.68%,参数量仅为0.74 M,基本满足工程化应用的需求。This paper proposes an improvement strategy for the SqueezeNet neural network.By deleting the third Maxpooling layer and setting the convolution kernel size of the first convolutional layer to 3 × 3,a lightweight SqueezeNet-Tiny model is created.The effectiveness of the improvement is verified on the Recyclable Waste Dataset (RW Dataset) with complex background.The SqueezeNet-Tiny is migrated to hardware facilities,and the design and production of intelligent sorting garbage cans are completed.The recognition accuracy can reach 94.68%,and the parameter quantity is only 0.74 M,which basically meets the needs of engineering applications.

关 键 词：SqueezeNet 可回收垃圾 智能分类垃圾桶 工业应用 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]