Loading…

An improved target detection method based on YOLOv5 in natural orchard environments

•An efficient method is proposed for orchard tree trunk detection in natural scenes.•A multi-scenes orchard tree trunk dataset is established for experiments.•The YOLOv5 model structure is improved to enhance detection accuracy and speed.•Proposed method is robust against complex orchard environment...

Full description

Saved in:
Bibliographic Details
Published in:Computers and electronics in agriculture 2024-04, Vol.219, p.108780, Article 108780
Main Authors: Zhang, Jiachuang, Tian, Mimi, Yang, Zengrong, Li, Junhui, Zhao, Longlian
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c306t-33a326edef8f5b7c0d1cfe49c0e99c96f65403755e9426619197999de8274c0e3
cites cdi_FETCH-LOGICAL-c306t-33a326edef8f5b7c0d1cfe49c0e99c96f65403755e9426619197999de8274c0e3
container_end_page
container_issue
container_start_page 108780
container_title Computers and electronics in agriculture
container_volume 219
creator Zhang, Jiachuang
Tian, Mimi
Yang, Zengrong
Li, Junhui
Zhao, Longlian
description •An efficient method is proposed for orchard tree trunk detection in natural scenes.•A multi-scenes orchard tree trunk dataset is established for experiments.•The YOLOv5 model structure is improved to enhance detection accuracy and speed.•Proposed method is robust against complex orchard environment. The recognition and localization of fruit tree trunks in orchard are important for orchard operation robots, which are the bases for automatic navigation, fruit tree spraying and fertilization etc. A method was proposed based on machine vision to detect target objects such as fruit tree trunks, person and supporters in orchard by improving the YOLOv5 deep learning algorithm in this paper, which is applicable to the recognition tasks in natural orchard environments. Firstly, 1354 images of the natural orchard collected by camera were image enhanced, weather effects such as rain, snow, bright light, shadow and fog were added to expand the dataset and to increase the robustness of the model. Secondly, the original YOLOv5 model was improved by replacing the Bottleneck network in the C3 module with the lightweight GhostNet V2 to reduce the network parameters, and changing the box loss function CIoU to SIoU in the loss function to make the regression of the detection box more accurate, and coordinate attention mechanism (CA) was added to the network to reduce the interference of useless background information in images. Before training, pre-anchor boxes were generated by using IoU-based K-means clustering, after that the dataset was fed into the improved YOLOv5 for training, and the trained model was used to detect the trunks. Finally, weighted boxes fusion (WBF) was used instead of the non-maximum suppression (NMS) in this paper for the output of the detection boxes. Then the density-based spatial clustering of applications with noise (DBSCAN) algorithm was used for trunk clustering. The improved target detection method was trained and validated on the experimental dataset. The model size is reduced by 43.6 %, model parameters are reduced by 46.9 %, and the mAP reaches 97.1 %, with an average detection speed of 198.2 ms per image. Compared with the original YOLOv5, the model is more lightweight, the detection accuracy and speed are improved. The improved YOLOv5 is also better than YOLOv3, NanoDet and SSD in terms of combined accuracy and speed, and has similar performance to YOLO_MobileNet in orchard dataset. The experimental results show that the improved YOLOv5 t
doi_str_mv 10.1016/j.compag.2024.108780
format article
fullrecord <record><control><sourceid>elsevier_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1016_j_compag_2024_108780</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0168169924001716</els_id><sourcerecordid>S0168169924001716</sourcerecordid><originalsourceid>FETCH-LOGICAL-c306t-33a326edef8f5b7c0d1cfe49c0e99c96f65403755e9426619197999de8274c0e3</originalsourceid><addsrcrecordid>eNp9kMtKQzEQhoMoWKtv4CIvcGpyLrlshFK8QaELdeEqpMmcNqUnKUk84Nubcly7Gv6Z_x9mPoTuKVlQQtnDYWHCcNK7RU3qtrQEF-QCzajgdcUp4ZdoVmyiokzKa3ST0oEULQWfofelx244xTCCxVnHHWRsIYPJLng8QN4Hi7c6lWnRX5v1Zuyw89jr_B31EYdo9jpaDH50MfgBfE636KrXxwR3f3WOPp-fPlav1Xrz8rZarivTEJarptFNzcBCL_puyw2x1PTQSkNASiNZz7qWNLzrQLY1Y1RSyaWUFkTN22Jq5qid9poYUorQq1N0g44_ihJ1BqMOagKjzmDUBKbEHqcYlNtGB1El48AbsC6Wv5UN7v8Fv0AMbj8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>An improved target detection method based on YOLOv5 in natural orchard environments</title><source>ScienceDirect Freedom Collection 2022-2024</source><creator>Zhang, Jiachuang ; Tian, Mimi ; Yang, Zengrong ; Li, Junhui ; Zhao, Longlian</creator><creatorcontrib>Zhang, Jiachuang ; Tian, Mimi ; Yang, Zengrong ; Li, Junhui ; Zhao, Longlian</creatorcontrib><description>•An efficient method is proposed for orchard tree trunk detection in natural scenes.•A multi-scenes orchard tree trunk dataset is established for experiments.•The YOLOv5 model structure is improved to enhance detection accuracy and speed.•Proposed method is robust against complex orchard environment. The recognition and localization of fruit tree trunks in orchard are important for orchard operation robots, which are the bases for automatic navigation, fruit tree spraying and fertilization etc. A method was proposed based on machine vision to detect target objects such as fruit tree trunks, person and supporters in orchard by improving the YOLOv5 deep learning algorithm in this paper, which is applicable to the recognition tasks in natural orchard environments. Firstly, 1354 images of the natural orchard collected by camera were image enhanced, weather effects such as rain, snow, bright light, shadow and fog were added to expand the dataset and to increase the robustness of the model. Secondly, the original YOLOv5 model was improved by replacing the Bottleneck network in the C3 module with the lightweight GhostNet V2 to reduce the network parameters, and changing the box loss function CIoU to SIoU in the loss function to make the regression of the detection box more accurate, and coordinate attention mechanism (CA) was added to the network to reduce the interference of useless background information in images. Before training, pre-anchor boxes were generated by using IoU-based K-means clustering, after that the dataset was fed into the improved YOLOv5 for training, and the trained model was used to detect the trunks. Finally, weighted boxes fusion (WBF) was used instead of the non-maximum suppression (NMS) in this paper for the output of the detection boxes. Then the density-based spatial clustering of applications with noise (DBSCAN) algorithm was used for trunk clustering. The improved target detection method was trained and validated on the experimental dataset. The model size is reduced by 43.6 %, model parameters are reduced by 46.9 %, and the mAP reaches 97.1 %, with an average detection speed of 198.2 ms per image. Compared with the original YOLOv5, the model is more lightweight, the detection accuracy and speed are improved. The improved YOLOv5 is also better than YOLOv3, NanoDet and SSD in terms of combined accuracy and speed, and has similar performance to YOLO_MobileNet in orchard dataset. The experimental results show that the improved YOLOv5 target detection model proposed in this paper is lightweight while still having better detection accuracy and detection speed in complex environments, and the model is small enough to be deployed to mobile or low-performance terminals for target detection in natural orchard environments.</description><identifier>ISSN: 0168-1699</identifier><identifier>EISSN: 1872-7107</identifier><identifier>DOI: 10.1016/j.compag.2024.108780</identifier><language>eng</language><publisher>Elsevier B.V</publisher><subject>Coordinate Attention ; Deep learning ; Target detection ; YOLOv5</subject><ispartof>Computers and electronics in agriculture, 2024-04, Vol.219, p.108780, Article 108780</ispartof><rights>2024 Elsevier B.V.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c306t-33a326edef8f5b7c0d1cfe49c0e99c96f65403755e9426619197999de8274c0e3</citedby><cites>FETCH-LOGICAL-c306t-33a326edef8f5b7c0d1cfe49c0e99c96f65403755e9426619197999de8274c0e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Zhang, Jiachuang</creatorcontrib><creatorcontrib>Tian, Mimi</creatorcontrib><creatorcontrib>Yang, Zengrong</creatorcontrib><creatorcontrib>Li, Junhui</creatorcontrib><creatorcontrib>Zhao, Longlian</creatorcontrib><title>An improved target detection method based on YOLOv5 in natural orchard environments</title><title>Computers and electronics in agriculture</title><description>•An efficient method is proposed for orchard tree trunk detection in natural scenes.•A multi-scenes orchard tree trunk dataset is established for experiments.•The YOLOv5 model structure is improved to enhance detection accuracy and speed.•Proposed method is robust against complex orchard environment. The recognition and localization of fruit tree trunks in orchard are important for orchard operation robots, which are the bases for automatic navigation, fruit tree spraying and fertilization etc. A method was proposed based on machine vision to detect target objects such as fruit tree trunks, person and supporters in orchard by improving the YOLOv5 deep learning algorithm in this paper, which is applicable to the recognition tasks in natural orchard environments. Firstly, 1354 images of the natural orchard collected by camera were image enhanced, weather effects such as rain, snow, bright light, shadow and fog were added to expand the dataset and to increase the robustness of the model. Secondly, the original YOLOv5 model was improved by replacing the Bottleneck network in the C3 module with the lightweight GhostNet V2 to reduce the network parameters, and changing the box loss function CIoU to SIoU in the loss function to make the regression of the detection box more accurate, and coordinate attention mechanism (CA) was added to the network to reduce the interference of useless background information in images. Before training, pre-anchor boxes were generated by using IoU-based K-means clustering, after that the dataset was fed into the improved YOLOv5 for training, and the trained model was used to detect the trunks. Finally, weighted boxes fusion (WBF) was used instead of the non-maximum suppression (NMS) in this paper for the output of the detection boxes. Then the density-based spatial clustering of applications with noise (DBSCAN) algorithm was used for trunk clustering. The improved target detection method was trained and validated on the experimental dataset. The model size is reduced by 43.6 %, model parameters are reduced by 46.9 %, and the mAP reaches 97.1 %, with an average detection speed of 198.2 ms per image. Compared with the original YOLOv5, the model is more lightweight, the detection accuracy and speed are improved. The improved YOLOv5 is also better than YOLOv3, NanoDet and SSD in terms of combined accuracy and speed, and has similar performance to YOLO_MobileNet in orchard dataset. The experimental results show that the improved YOLOv5 target detection model proposed in this paper is lightweight while still having better detection accuracy and detection speed in complex environments, and the model is small enough to be deployed to mobile or low-performance terminals for target detection in natural orchard environments.</description><subject>Coordinate Attention</subject><subject>Deep learning</subject><subject>Target detection</subject><subject>YOLOv5</subject><issn>0168-1699</issn><issn>1872-7107</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kMtKQzEQhoMoWKtv4CIvcGpyLrlshFK8QaELdeEqpMmcNqUnKUk84Nubcly7Gv6Z_x9mPoTuKVlQQtnDYWHCcNK7RU3qtrQEF-QCzajgdcUp4ZdoVmyiokzKa3ST0oEULQWfofelx244xTCCxVnHHWRsIYPJLng8QN4Hi7c6lWnRX5v1Zuyw89jr_B31EYdo9jpaDH50MfgBfE636KrXxwR3f3WOPp-fPlav1Xrz8rZarivTEJarptFNzcBCL_puyw2x1PTQSkNASiNZz7qWNLzrQLY1Y1RSyaWUFkTN22Jq5qid9poYUorQq1N0g44_ihJ1BqMOagKjzmDUBKbEHqcYlNtGB1El48AbsC6Wv5UN7v8Fv0AMbj8</recordid><startdate>202404</startdate><enddate>202404</enddate><creator>Zhang, Jiachuang</creator><creator>Tian, Mimi</creator><creator>Yang, Zengrong</creator><creator>Li, Junhui</creator><creator>Zhao, Longlian</creator><general>Elsevier B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>202404</creationdate><title>An improved target detection method based on YOLOv5 in natural orchard environments</title><author>Zhang, Jiachuang ; Tian, Mimi ; Yang, Zengrong ; Li, Junhui ; Zhao, Longlian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c306t-33a326edef8f5b7c0d1cfe49c0e99c96f65403755e9426619197999de8274c0e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Coordinate Attention</topic><topic>Deep learning</topic><topic>Target detection</topic><topic>YOLOv5</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Jiachuang</creatorcontrib><creatorcontrib>Tian, Mimi</creatorcontrib><creatorcontrib>Yang, Zengrong</creatorcontrib><creatorcontrib>Li, Junhui</creatorcontrib><creatorcontrib>Zhao, Longlian</creatorcontrib><collection>CrossRef</collection><jtitle>Computers and electronics in agriculture</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Jiachuang</au><au>Tian, Mimi</au><au>Yang, Zengrong</au><au>Li, Junhui</au><au>Zhao, Longlian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An improved target detection method based on YOLOv5 in natural orchard environments</atitle><jtitle>Computers and electronics in agriculture</jtitle><date>2024-04</date><risdate>2024</risdate><volume>219</volume><spage>108780</spage><pages>108780-</pages><artnum>108780</artnum><issn>0168-1699</issn><eissn>1872-7107</eissn><abstract>•An efficient method is proposed for orchard tree trunk detection in natural scenes.•A multi-scenes orchard tree trunk dataset is established for experiments.•The YOLOv5 model structure is improved to enhance detection accuracy and speed.•Proposed method is robust against complex orchard environment. The recognition and localization of fruit tree trunks in orchard are important for orchard operation robots, which are the bases for automatic navigation, fruit tree spraying and fertilization etc. A method was proposed based on machine vision to detect target objects such as fruit tree trunks, person and supporters in orchard by improving the YOLOv5 deep learning algorithm in this paper, which is applicable to the recognition tasks in natural orchard environments. Firstly, 1354 images of the natural orchard collected by camera were image enhanced, weather effects such as rain, snow, bright light, shadow and fog were added to expand the dataset and to increase the robustness of the model. Secondly, the original YOLOv5 model was improved by replacing the Bottleneck network in the C3 module with the lightweight GhostNet V2 to reduce the network parameters, and changing the box loss function CIoU to SIoU in the loss function to make the regression of the detection box more accurate, and coordinate attention mechanism (CA) was added to the network to reduce the interference of useless background information in images. Before training, pre-anchor boxes were generated by using IoU-based K-means clustering, after that the dataset was fed into the improved YOLOv5 for training, and the trained model was used to detect the trunks. Finally, weighted boxes fusion (WBF) was used instead of the non-maximum suppression (NMS) in this paper for the output of the detection boxes. Then the density-based spatial clustering of applications with noise (DBSCAN) algorithm was used for trunk clustering. The improved target detection method was trained and validated on the experimental dataset. The model size is reduced by 43.6 %, model parameters are reduced by 46.9 %, and the mAP reaches 97.1 %, with an average detection speed of 198.2 ms per image. Compared with the original YOLOv5, the model is more lightweight, the detection accuracy and speed are improved. The improved YOLOv5 is also better than YOLOv3, NanoDet and SSD in terms of combined accuracy and speed, and has similar performance to YOLO_MobileNet in orchard dataset. The experimental results show that the improved YOLOv5 target detection model proposed in this paper is lightweight while still having better detection accuracy and detection speed in complex environments, and the model is small enough to be deployed to mobile or low-performance terminals for target detection in natural orchard environments.</abstract><pub>Elsevier B.V</pub><doi>10.1016/j.compag.2024.108780</doi></addata></record>
fulltext fulltext
identifier ISSN: 0168-1699
ispartof Computers and electronics in agriculture, 2024-04, Vol.219, p.108780, Article 108780
issn 0168-1699
1872-7107
language eng
recordid cdi_crossref_primary_10_1016_j_compag_2024_108780
source ScienceDirect Freedom Collection 2022-2024
subjects Coordinate Attention
Deep learning
Target detection
YOLOv5
title An improved target detection method based on YOLOv5 in natural orchard environments
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T13%3A56%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20improved%20target%20detection%20method%20based%20on%20YOLOv5%20in%20natural%20orchard%20environments&rft.jtitle=Computers%20and%20electronics%20in%20agriculture&rft.au=Zhang,%20Jiachuang&rft.date=2024-04&rft.volume=219&rft.spage=108780&rft.pages=108780-&rft.artnum=108780&rft.issn=0168-1699&rft.eissn=1872-7107&rft_id=info:doi/10.1016/j.compag.2024.108780&rft_dat=%3Celsevier_cross%3ES0168169924001716%3C/elsevier_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c306t-33a326edef8f5b7c0d1cfe49c0e99c96f65403755e9426619197999de8274c0e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true