Cargando…

Polar-Net: Green fruit instance segmentation in complex orchard environment

High-quality orchard picking has become a new trend, and achieving the picking of homogeneous fruit is a huge challenge for picking robots. Based on the premise of improving picking efficiency of homo-chromatic fruit in complex environments, this paper proposes a novel homo-chromatic fruit segmentat...

Descripción completa

Detalles Bibliográficos
Autores principales: Jia, Weikuan, Liu, Jie, Lu, Yuqi, Liu, Qiaolian, Zhang, Ting, Dong, Xishang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9796563/
https://www.ncbi.nlm.nih.gov/pubmed/36589132
http://dx.doi.org/10.3389/fpls.2022.1054007
_version_ 1784860514381201408
author Jia, Weikuan
Liu, Jie
Lu, Yuqi
Liu, Qiaolian
Zhang, Ting
Dong, Xishang
author_facet Jia, Weikuan
Liu, Jie
Lu, Yuqi
Liu, Qiaolian
Zhang, Ting
Dong, Xishang
author_sort Jia, Weikuan
collection PubMed
description High-quality orchard picking has become a new trend, and achieving the picking of homogeneous fruit is a huge challenge for picking robots. Based on the premise of improving picking efficiency of homo-chromatic fruit in complex environments, this paper proposes a novel homo-chromatic fruit segmentation model under Polar-Net. The model uses Densely Connected Convolutional Networks (DenseNet) as the backbone network, Feature Pyramid Network (FPN) and Cross Feature Network (CFN) to achieve feature extraction and feature discrimination for images of different scales, regions of interest are drawn with the help of Region Proposal Network (RPN), and regression is performed between the features of different layers. In the result prediction part, polar coordinate modeling is performed based on the extracted image features, and the instance segmentation problem is reduced to predict the instance contour for instance center classification and dense distance regression. Experimental results demonstrate that the method effectively improves the segmentation accuracy of homo-chromatic objects and has the characteristics of simplicity and efficiency. The new method has improved the accuracy of segmentation of homo-chromatic objects for picking robots and also provides a reference for segmentation of other fruit and vegetables.
format Online
Article
Text
id pubmed-9796563
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-97965632022-12-29 Polar-Net: Green fruit instance segmentation in complex orchard environment Jia, Weikuan Liu, Jie Lu, Yuqi Liu, Qiaolian Zhang, Ting Dong, Xishang Front Plant Sci Plant Science High-quality orchard picking has become a new trend, and achieving the picking of homogeneous fruit is a huge challenge for picking robots. Based on the premise of improving picking efficiency of homo-chromatic fruit in complex environments, this paper proposes a novel homo-chromatic fruit segmentation model under Polar-Net. The model uses Densely Connected Convolutional Networks (DenseNet) as the backbone network, Feature Pyramid Network (FPN) and Cross Feature Network (CFN) to achieve feature extraction and feature discrimination for images of different scales, regions of interest are drawn with the help of Region Proposal Network (RPN), and regression is performed between the features of different layers. In the result prediction part, polar coordinate modeling is performed based on the extracted image features, and the instance segmentation problem is reduced to predict the instance contour for instance center classification and dense distance regression. Experimental results demonstrate that the method effectively improves the segmentation accuracy of homo-chromatic objects and has the characteristics of simplicity and efficiency. The new method has improved the accuracy of segmentation of homo-chromatic objects for picking robots and also provides a reference for segmentation of other fruit and vegetables. Frontiers Media S.A. 2022-12-14 /pmc/articles/PMC9796563/ /pubmed/36589132 http://dx.doi.org/10.3389/fpls.2022.1054007 Text en Copyright © 2022 Jia, Liu, Lu, Liu, Zhang and Dong 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
Liu, Jie
Lu, Yuqi
Liu, Qiaolian
Zhang, Ting
Dong, Xishang
Polar-Net: Green fruit instance segmentation in complex orchard environment
title Polar-Net: Green fruit instance segmentation in complex orchard environment
title_full Polar-Net: Green fruit instance segmentation in complex orchard environment
title_fullStr Polar-Net: Green fruit instance segmentation in complex orchard environment
title_full_unstemmed Polar-Net: Green fruit instance segmentation in complex orchard environment
title_short Polar-Net: Green fruit instance segmentation in complex orchard environment
title_sort polar-net: green fruit instance segmentation in complex orchard environment
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9796563/
https://www.ncbi.nlm.nih.gov/pubmed/36589132
http://dx.doi.org/10.3389/fpls.2022.1054007
work_keys_str_mv AT jiaweikuan polarnetgreenfruitinstancesegmentationincomplexorchardenvironment
AT liujie polarnetgreenfruitinstancesegmentationincomplexorchardenvironment
AT luyuqi polarnetgreenfruitinstancesegmentationincomplexorchardenvironment
AT liuqiaolian polarnetgreenfruitinstancesegmentationincomplexorchardenvironment
AT zhangting polarnetgreenfruitinstancesegmentationincomplexorchardenvironment
AT dongxishang polarnetgreenfruitinstancesegmentationincomplexorchardenvironment