Cargando…

An accurate green fruits detection method based on optimized YOLOX-m

Fruit detection and recognition has an important impact on fruit and vegetable harvesting, yield prediction and growth information monitoring in the automation process of modern agriculture, and the actual complex environment of orchards poses some challenges for accurate fruit detection. In order t...

Descripción completa

Detalles Bibliográficos
Autores principales: Jia, Weikuan, Xu, Ying, Lu, Yuqi, Yin, Xiang, Pan, Ningning, Jiang, Ru, Ge, Xinting
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10200941/
https://www.ncbi.nlm.nih.gov/pubmed/37223802
http://dx.doi.org/10.3389/fpls.2023.1187734
_version_ 1785045160685469696
author Jia, Weikuan
Xu, Ying
Lu, Yuqi
Yin, Xiang
Pan, Ningning
Jiang, Ru
Ge, Xinting
author_facet Jia, Weikuan
Xu, Ying
Lu, Yuqi
Yin, Xiang
Pan, Ningning
Jiang, Ru
Ge, Xinting
author_sort Jia, Weikuan
collection PubMed
description Fruit detection and recognition has an important impact on fruit and vegetable harvesting, yield prediction and growth information monitoring in the automation process of modern agriculture, and the actual complex environment of orchards poses some challenges for accurate fruit detection. In order to achieve accurate detection of green fruits in complex orchard environments, this paper proposes an accurate object detection method for green fruits based on optimized YOLOX_m. First, the model extracts features from the input image using the CSPDarkNet backbone network to obtain three effective feature layers at different scales. Then, these effective feature layers are fed into the feature fusion pyramid network for enhanced feature extraction, which combines feature information from different scales, and in this process, the Atrous spatial pyramid pooling (ASPP) module is used to increase the receptive field and enhance the network’s ability to obtain multi-scale contextual information. Finally, the fused features are fed into the head prediction network for classification prediction and regression prediction. In addition, Varifocal loss is used to mitigate the negative impact of unbalanced distribution of positive and negative samples to obtain higher precision. The experimental results show that the model in this paper has improved on both apple and persimmon datasets, with the average precision (AP) reaching 64.3% and 74.7%, respectively. Compared with other models commonly used for detection, the model approach in this study has a higher average precision and has improved in other performance metrics, which can provide a reference for the detection of other fruits and vegetables.
format Online
Article
Text
id pubmed-10200941
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-102009412023-05-23 An accurate green fruits detection method based on optimized YOLOX-m Jia, Weikuan Xu, Ying Lu, Yuqi Yin, Xiang Pan, Ningning Jiang, Ru Ge, Xinting Front Plant Sci Plant Science Fruit detection and recognition has an important impact on fruit and vegetable harvesting, yield prediction and growth information monitoring in the automation process of modern agriculture, and the actual complex environment of orchards poses some challenges for accurate fruit detection. In order to achieve accurate detection of green fruits in complex orchard environments, this paper proposes an accurate object detection method for green fruits based on optimized YOLOX_m. First, the model extracts features from the input image using the CSPDarkNet backbone network to obtain three effective feature layers at different scales. Then, these effective feature layers are fed into the feature fusion pyramid network for enhanced feature extraction, which combines feature information from different scales, and in this process, the Atrous spatial pyramid pooling (ASPP) module is used to increase the receptive field and enhance the network’s ability to obtain multi-scale contextual information. Finally, the fused features are fed into the head prediction network for classification prediction and regression prediction. In addition, Varifocal loss is used to mitigate the negative impact of unbalanced distribution of positive and negative samples to obtain higher precision. The experimental results show that the model in this paper has improved on both apple and persimmon datasets, with the average precision (AP) reaching 64.3% and 74.7%, respectively. Compared with other models commonly used for detection, the model approach in this study has a higher average precision and has improved in other performance metrics, which can provide a reference for the detection of other fruits and vegetables. Frontiers Media S.A. 2023-05-08 /pmc/articles/PMC10200941/ /pubmed/37223802 http://dx.doi.org/10.3389/fpls.2023.1187734 Text en Copyright © 2023 Jia, Xu, Lu, Yin, Pan, Jiang and Ge https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Jia, Weikuan
Xu, Ying
Lu, Yuqi
Yin, Xiang
Pan, Ningning
Jiang, Ru
Ge, Xinting
An accurate green fruits detection method based on optimized YOLOX-m
title An accurate green fruits detection method based on optimized YOLOX-m
title_full An accurate green fruits detection method based on optimized YOLOX-m
title_fullStr An accurate green fruits detection method based on optimized YOLOX-m
title_full_unstemmed An accurate green fruits detection method based on optimized YOLOX-m
title_short An accurate green fruits detection method based on optimized YOLOX-m
title_sort accurate green fruits detection method based on optimized yolox-m
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10200941/
https://www.ncbi.nlm.nih.gov/pubmed/37223802
http://dx.doi.org/10.3389/fpls.2023.1187734
work_keys_str_mv AT jiaweikuan anaccurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT xuying anaccurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT luyuqi anaccurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT yinxiang anaccurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT panningning anaccurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT jiangru anaccurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT gexinting anaccurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT jiaweikuan accurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT xuying accurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT luyuqi accurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT yinxiang accurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT panningning accurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT jiangru accurategreenfruitsdetectionmethodbasedonoptimizedyoloxm
AT gexinting accurategreenfruitsdetectionmethodbasedonoptimizedyoloxm