基于深度学习与视觉算法的垃圾分类装置设计

Design of garbage classification device based on deep learning and visual algorithm

为了应对日益严峻的垃圾分类挑战,设计了一款基于机器学习与视觉算法的垃圾分类装置。本系统通过摄像头采集数据并由Maix bit核心板进行分类,其中应用的机器学习网络MobileNet与视觉模块中的归一化算法使得分类精度大幅提升。系统分类后,Maix bit核心板与STM32F103板进行通信,控制对应舵机与语音播报系统,实现对相应类型垃圾的分类操作。通过实验验证,本装置垃圾分辨时间小于1 s,分辨精度高于98%,因此在现实中具有很高的实用性。

In order to cope with the increasingly severe challenge of waste classification,this paper designs a waste sorting device based on machine learning and vision algorithms.The device collects data from the video camera and sorts them by the Maix bit core board,in which the machine learning network MobileNet and the normalization algorithm in the vision module are applied to increase the sorting accuracy dramatically.After classification,the Maix bit core board communicates with the STM32F103 board to control the corresponding servo and the speech announce system to implement the sorting operation for the relevant type of waste.After experimental validation,this device can achieve garbage sorting speeds of less than 1 second and accuracy greater than 98%.Therefore,it possesses strong practicality in real applications.