AUTORECYCLER: Prototype based on artificial vision to automate the material classification process (Plastic, Glass, Cardboard and Metal)

IF 2 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC HardwareX Pub Date : 2024-09-01 DOI:10.1016/j.ohx.2024.e00575

Anggie P. Echeverry , Carlos F. López

{"title":"AUTORECYCLER: Prototype based on artificial vision to automate the material classification process (Plastic, Glass, Cardboard and Metal)","authors":"Anggie P. Echeverry , Carlos F. López","doi":"10.1016/j.ohx.2024.e00575","DOIUrl":null,"url":null,"abstract":"<div><p>Environmental protection has gained greater importance over time due to the negative impact and irreversible consequences that have occurred worldwide and stem from pollution. One of the great challenges faced in different parts of the world is the inadequate management and classification of solid waste. In order to contribute to tackling this issue, this paper proposes an automated sorting system based on artificial vision which allows recognition and separation of recyclable materials (Plastic, Glass, Cardboard and Metal) through a webcam connected in real time to the Nvidia® Jetson Nano™ 2 GB programming board, which has a convolutional neural network (CNN) trained for the proper classification of waste. The system had a 95 % accuracy in separating plastic, 96 % in glass and metal, and 94 % in cardboard. With this in mind, we conclude it contributes to the recycling effort, which has an impact on the reduction of environmental pollution worldwide.</p></div>","PeriodicalId":37503,"journal":{"name":"HardwareX","volume":null,"pages":null},"PeriodicalIF":2.0000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2468067224000695/pdfft?md5=4afa327ad0be22153064f4735719a2d9&pid=1-s2.0-S2468067224000695-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"HardwareX","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2468067224000695","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

Environmental protection has gained greater importance over time due to the negative impact and irreversible consequences that have occurred worldwide and stem from pollution. One of the great challenges faced in different parts of the world is the inadequate management and classification of solid waste. In order to contribute to tackling this issue, this paper proposes an automated sorting system based on artificial vision which allows recognition and separation of recyclable materials (Plastic, Glass, Cardboard and Metal) through a webcam connected in real time to the Nvidia® Jetson Nano™ 2 GB programming board, which has a convolutional neural network (CNN) trained for the proper classification of waste. The system had a 95 % accuracy in separating plastic, 96 % in glass and metal, and 94 % in cardboard. With this in mind, we conclude it contributes to the recycling effort, which has an impact on the reduction of environmental pollution worldwide.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

AUTORECYCLER：基于人工视觉的原型，用于自动进行材料分类（塑料、玻璃、纸板和金属）。

随着时间的推移，由于污染在全球范围内造成的负面影响和不可逆转的后果，环境保护变得越来越重要。世界各地面临的巨大挑战之一是固体废物的管理和分类不足。为了解决这一问题，本文提出了一种基于人工视觉的自动分类系统，该系统可通过与 Nvidia® Jetson Nano™ 2 GB 编程板实时连接的网络摄像头识别和分离可回收材料（塑料、玻璃、纸板和金属）。该系统对塑料的分类准确率为 95%，对玻璃和金属的分类准确率为 96%，对纸板的分类准确率为 94%。有鉴于此，我们得出结论，该系统有助于回收工作，从而对减少全球环境污染产生影响。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

HardwareX Engineering-Industrial and Manufacturing Engineering

CiteScore

4.10

自引率

18.20%

发文量

124

审稿时长

24 weeks

期刊介绍： HardwareX is an open access journal established to promote free and open source designing, building and customizing of scientific infrastructure (hardware). HardwareX aims to recognize researchers for the time and effort in developing scientific infrastructure while providing end-users with sufficient information to replicate and validate the advances presented. HardwareX is open to input from all scientific, technological and medical disciplines. Scientific infrastructure will be interpreted in the broadest sense. Including hardware modifications to existing infrastructure, sensors and tools that perform measurements and other functions outside of the traditional lab setting (such as wearables, air/water quality sensors, and low cost alternatives to existing tools), and the creation of wholly new tools for either standard or novel laboratory tasks. Authors are encouraged to submit hardware developments that address all aspects of science, not only the final measurement, for example, enhancements in sample preparation and handling, user safety, and quality control. The use of distributed digital manufacturing strategies (e.g. 3-D printing) is encouraged. All designs must be submitted under an open hardware license.