Cargando…

Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion

Microplastic particles produced by non-degradable waste plastic bottles have a critical impact on the environment. Reasonable recycling is a premise that protects the environment and improves economic benefits. In this paper, a multi-scale feature fusion method for RGB and hyperspectral images based...

Descripción completa

Detalles Bibliográficos
Autores principales: Cai, Zhenxing, Yang, Jianhong, Fang, Huaiying, Ji, Tianchen, Hu, Yangyang, Wang, Xin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9609436/
https://www.ncbi.nlm.nih.gov/pubmed/36298325
http://dx.doi.org/10.3390/s22207974
_version_ 1784819018829398016
author Cai, Zhenxing
Yang, Jianhong
Fang, Huaiying
Ji, Tianchen
Hu, Yangyang
Wang, Xin
author_facet Cai, Zhenxing
Yang, Jianhong
Fang, Huaiying
Ji, Tianchen
Hu, Yangyang
Wang, Xin
author_sort Cai, Zhenxing
collection PubMed
description Microplastic particles produced by non-degradable waste plastic bottles have a critical impact on the environment. Reasonable recycling is a premise that protects the environment and improves economic benefits. In this paper, a multi-scale feature fusion method for RGB and hyperspectral images based on Segmenting Objects by Locations (RHFF-SOLOv1) is proposed, which uses multi-sensor fusion technology to improve the accuracy of identifying transparent polyethylene terephthalate (PET) bottles, blue PET bottles, and transparent polypropylene (PP) bottles on a black conveyor belt. A line-scan camera and near-infrared (NIR) hyperspectral camera covering the spectral range from 935.9 nm to 1722.5 nm are used to obtain RGB and hyperspectral images synchronously. Moreover, we propose a hyperspectral feature band selection method that effectively reduces the dimensionality and selects the bands from 1087.6 nm to 1285.1 nm as the features of the hyperspectral image. The results show that the proposed fusion method improves the accuracy of plastic bottle classification compared with the SOLOv1 method, and the overall accuracy is 95.55%. Finally, compared with other space-spectral fusion methods, RHFF-SOLOv1 is superior to most of them and achieves the best (97.5%) accuracy in blue bottle classification.
format Online
Article
Text
id pubmed-9609436
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96094362022-10-28 Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion Cai, Zhenxing Yang, Jianhong Fang, Huaiying Ji, Tianchen Hu, Yangyang Wang, Xin Sensors (Basel) Article Microplastic particles produced by non-degradable waste plastic bottles have a critical impact on the environment. Reasonable recycling is a premise that protects the environment and improves economic benefits. In this paper, a multi-scale feature fusion method for RGB and hyperspectral images based on Segmenting Objects by Locations (RHFF-SOLOv1) is proposed, which uses multi-sensor fusion technology to improve the accuracy of identifying transparent polyethylene terephthalate (PET) bottles, blue PET bottles, and transparent polypropylene (PP) bottles on a black conveyor belt. A line-scan camera and near-infrared (NIR) hyperspectral camera covering the spectral range from 935.9 nm to 1722.5 nm are used to obtain RGB and hyperspectral images synchronously. Moreover, we propose a hyperspectral feature band selection method that effectively reduces the dimensionality and selects the bands from 1087.6 nm to 1285.1 nm as the features of the hyperspectral image. The results show that the proposed fusion method improves the accuracy of plastic bottle classification compared with the SOLOv1 method, and the overall accuracy is 95.55%. Finally, compared with other space-spectral fusion methods, RHFF-SOLOv1 is superior to most of them and achieves the best (97.5%) accuracy in blue bottle classification. MDPI 2022-10-19 /pmc/articles/PMC9609436/ /pubmed/36298325 http://dx.doi.org/10.3390/s22207974 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Cai, Zhenxing
Yang, Jianhong
Fang, Huaiying
Ji, Tianchen
Hu, Yangyang
Wang, Xin
Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion
title Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion
title_full Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion
title_fullStr Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion
title_full_unstemmed Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion
title_short Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion
title_sort research on waste plastics classification method based on multi-scale feature fusion
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9609436/
https://www.ncbi.nlm.nih.gov/pubmed/36298325
http://dx.doi.org/10.3390/s22207974
work_keys_str_mv AT caizhenxing researchonwasteplasticsclassificationmethodbasedonmultiscalefeaturefusion
AT yangjianhong researchonwasteplasticsclassificationmethodbasedonmultiscalefeaturefusion
AT fanghuaiying researchonwasteplasticsclassificationmethodbasedonmultiscalefeaturefusion
AT jitianchen researchonwasteplasticsclassificationmethodbasedonmultiscalefeaturefusion
AT huyangyang researchonwasteplasticsclassificationmethodbasedonmultiscalefeaturefusion
AT wangxin researchonwasteplasticsclassificationmethodbasedonmultiscalefeaturefusion