Garbage classification system based on improved ShuffleNet v2

Zhichao Chen

doi:10.1016/j.resconrec.2021.106090

2022-03-01

PRE

DOI：10.1016/j.resconrec.2021.106090

原文链接

原文求助

摘要

En 中文

Garbage classification technology is not only an important basis for the harmless treatment of waste and resource recovery, but also the inevitable trend of social development. The current garbage classification methods rely on manual classification in the garbage collection stage, and it is difficult to achieve satisfying results in consistency, stability, and sanitary conditions. For this reason, this study designs and develops a garbage classification system based on deep learning that can recognize and recycle domestic garbage. Focusing on the problems of low accuracy and poor real-time performance, a lightweight garbage classification model GCNet (Garbage Classification Network) is proposed. GCNet contains three improvements on ShuffleNet v2, including the design of parallel mixed attention mechanism (PMAM), the use of new activation functions, and transfer learning. The experimental results show that the average accuracy of GCNet on the self-built dataset is 97.9%, the amount of model parameters is only 1.3M, the single inference time on Raspberry Pi 4B is about 105ms, and the classification system needs only 0.88 seconds to complete the classification and collection of a single object. The method proposed in this paper is an effective attempt at machine vision in garbage classification and resource recovery. With the improvement of technology, it will effectively promote academic exploration and engineering application in the field of resources and environment.

Keyword:

Garbage image classification

ShuffleNet v2

Attention mechanism

Activation function

Transfer learning

Recycling

期刊

Resources Conservation and Recycling

IF:

10.9

论文数:

7.1K

被引数:

5.3W

机构

jiangxi university of science & technology

学者数:

6.7K

论文数: 4.5K

被引数: 3

引用论文

Grape disease image classification based on lightweight convolution neural networks and channelwise attention 基于轻量级卷积神经网络和通道注意力的葡萄病害图像分类

COMPUTERS AND ELECTRONICS IN AGRICULTURE

IF8.9

2020-11-01

112

PREAI

Tang, Zhe; Yang, Jialing; Li, Zhe; Qi, Fang

An AI-Based Visual Aid With Integrated Reading Assistant for the Completely Blind 一种基于人工智能的视觉辅助工具，带有全盲阅读助手

IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS

IF4.4

2020-12-01

PREAI

Khan, Muiz Ahmed; Paul, Pias; Rashid, Mahmudur; Hossain, Mainul; Ahad, Md Atiqur Rahman

Power Generation Performance of Polymer Electrolyte Fuel Cells with Electrocatalysts Supported on SnO₂ in High Current Density Range

ECS Transactions

IF0

2022-09-30

PREAI

Taichi Ogawa; Yusuke Inoue; Kotaro Yamamoto; Masahiro Yasutake; Zhiyun Noda; Stephen Matthew Lyth; Junko Matsuda; Masamichi Nishihara; Akari Hayashi; Kazunari Sasaki

WasNet: A Neural Network-Based Garbage Collection Management System

IEEE ACCESS

IF3.6

2020-01-01