Cargando…

A Domestic Trash Detection Model Based on Improved YOLOX

Domestic trash detection is an essential technology toward achieving a smart city. Due to the complexity and variability of urban trash scenarios, the existing trash detection algorithms suffer from low detection rates and high false positives, as well as the general problem of slow speed in industr...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Changhong, Xie, Ning, Yang, Xingxin, Chen, Rongdong, Chang, Xiangyang, Zhong, Ray Y., Peng, Shaohu, Liu, Xiaochu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9505880/
https://www.ncbi.nlm.nih.gov/pubmed/36146322
http://dx.doi.org/10.3390/s22186974
_version_ 1784796583753154560
author Liu, Changhong
Xie, Ning
Yang, Xingxin
Chen, Rongdong
Chang, Xiangyang
Zhong, Ray Y.
Peng, Shaohu
Liu, Xiaochu
author_facet Liu, Changhong
Xie, Ning
Yang, Xingxin
Chen, Rongdong
Chang, Xiangyang
Zhong, Ray Y.
Peng, Shaohu
Liu, Xiaochu
author_sort Liu, Changhong
collection PubMed
description Domestic trash detection is an essential technology toward achieving a smart city. Due to the complexity and variability of urban trash scenarios, the existing trash detection algorithms suffer from low detection rates and high false positives, as well as the general problem of slow speed in industrial applications. This paper proposes an i-YOLOX model for domestic trash detection based on deep learning algorithms. First, a large number of real-life trash images are collected into a new trash image dataset. Second, the lightweight operator involution is incorporated into the feature extraction structure of the algorithm, which allows the feature extraction layer to establish long-distance feature relationships and adaptively extract channel features. In addition, the ability of the model to distinguish similar trash features is strengthened by adding the convolutional block attention module (CBAM) to the enhanced feature extraction network. Finally, the design of the involution residual head structure in the detection head reduces the gradient disappearance and accelerates the convergence of the model loss values allowing the model to perform better classification and regression of the acquired feature layers. In this study, YOLOX-S is chosen as the baseline for each enhancement experiment. The experimental results show that compared with the baseline algorithm, the mean average precision (mAP) of i-YOLOX is improved by 1.47%, the number of parameters is reduced by 23.3%, and the FPS is improved by 40.4%. In practical applications, this improved model achieves accurate recognition of trash in natural scenes, which further validates the generalization performance of i-YOLOX and provides a reference for future domestic trash detection research.
format Online
Article
Text
id pubmed-9505880
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95058802022-09-24 A Domestic Trash Detection Model Based on Improved YOLOX Liu, Changhong Xie, Ning Yang, Xingxin Chen, Rongdong Chang, Xiangyang Zhong, Ray Y. Peng, Shaohu Liu, Xiaochu Sensors (Basel) Article Domestic trash detection is an essential technology toward achieving a smart city. Due to the complexity and variability of urban trash scenarios, the existing trash detection algorithms suffer from low detection rates and high false positives, as well as the general problem of slow speed in industrial applications. This paper proposes an i-YOLOX model for domestic trash detection based on deep learning algorithms. First, a large number of real-life trash images are collected into a new trash image dataset. Second, the lightweight operator involution is incorporated into the feature extraction structure of the algorithm, which allows the feature extraction layer to establish long-distance feature relationships and adaptively extract channel features. In addition, the ability of the model to distinguish similar trash features is strengthened by adding the convolutional block attention module (CBAM) to the enhanced feature extraction network. Finally, the design of the involution residual head structure in the detection head reduces the gradient disappearance and accelerates the convergence of the model loss values allowing the model to perform better classification and regression of the acquired feature layers. In this study, YOLOX-S is chosen as the baseline for each enhancement experiment. The experimental results show that compared with the baseline algorithm, the mean average precision (mAP) of i-YOLOX is improved by 1.47%, the number of parameters is reduced by 23.3%, and the FPS is improved by 40.4%. In practical applications, this improved model achieves accurate recognition of trash in natural scenes, which further validates the generalization performance of i-YOLOX and provides a reference for future domestic trash detection research. MDPI 2022-09-15 /pmc/articles/PMC9505880/ /pubmed/36146322 http://dx.doi.org/10.3390/s22186974 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
Liu, Changhong
Xie, Ning
Yang, Xingxin
Chen, Rongdong
Chang, Xiangyang
Zhong, Ray Y.
Peng, Shaohu
Liu, Xiaochu
A Domestic Trash Detection Model Based on Improved YOLOX
title A Domestic Trash Detection Model Based on Improved YOLOX
title_full A Domestic Trash Detection Model Based on Improved YOLOX
title_fullStr A Domestic Trash Detection Model Based on Improved YOLOX
title_full_unstemmed A Domestic Trash Detection Model Based on Improved YOLOX
title_short A Domestic Trash Detection Model Based on Improved YOLOX
title_sort domestic trash detection model based on improved yolox
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9505880/
https://www.ncbi.nlm.nih.gov/pubmed/36146322
http://dx.doi.org/10.3390/s22186974
work_keys_str_mv AT liuchanghong adomestictrashdetectionmodelbasedonimprovedyolox
AT xiening adomestictrashdetectionmodelbasedonimprovedyolox
AT yangxingxin adomestictrashdetectionmodelbasedonimprovedyolox
AT chenrongdong adomestictrashdetectionmodelbasedonimprovedyolox
AT changxiangyang adomestictrashdetectionmodelbasedonimprovedyolox
AT zhongrayy adomestictrashdetectionmodelbasedonimprovedyolox
AT pengshaohu adomestictrashdetectionmodelbasedonimprovedyolox
AT liuxiaochu adomestictrashdetectionmodelbasedonimprovedyolox
AT liuchanghong domestictrashdetectionmodelbasedonimprovedyolox
AT xiening domestictrashdetectionmodelbasedonimprovedyolox
AT yangxingxin domestictrashdetectionmodelbasedonimprovedyolox
AT chenrongdong domestictrashdetectionmodelbasedonimprovedyolox
AT changxiangyang domestictrashdetectionmodelbasedonimprovedyolox
AT zhongrayy domestictrashdetectionmodelbasedonimprovedyolox
AT pengshaohu domestictrashdetectionmodelbasedonimprovedyolox
AT liuxiaochu domestictrashdetectionmodelbasedonimprovedyolox