Loading…
YOLOv5s-BC: An improved YOLOv5s-based method for real-time apple detection
To address the issues associated with the existing algorithms for the current apple detection, this study proposes an improved YOLOv5s-based method, named YOLOv5s-BC, for real-time apple detection, in which a series of modifications have been introduced. Firstly, a coordinate attention (CA) block ha...
Saved in:
Published in: | arXiv.org 2023-11 |
---|---|
Main Authors: | , |
Format: | Article |
Language: | English |
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | |
container_end_page | |
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Liu, Jingfan Liu, Zhaobing |
description | To address the issues associated with the existing algorithms for the current apple detection, this study proposes an improved YOLOv5s-based method, named YOLOv5s-BC, for real-time apple detection, in which a series of modifications have been introduced. Firstly, a coordinate attention (CA) block has been incorporated into the backbone module to construct a new backbone network. Secondly, the original concatenation operation has been replaced with a bidirectional feature pyramid network (BiFPN) in the neck module. Lastly, a new detection head has been added to the head module, enabling the detection of smaller and more distant targets within the field of view of the robot. The proposed YOLOv5s-BC model was compared to several target detection algorithms, including YOLOv5s, YOLOv4, YOLOv3, SSD, Faster R-CNN (ResNet50), and Faster R-CNN (VGG), with significant improvements of 4.6%, 3.6%, 20.48%, 23.22%, 15.27%, and 15.59% in mAP, respectively. The detection accuracy of the proposed model is also greatly enhanced over the original YOLOv5s model. The model boasts an average detection speed of 0.018 seconds per image, and the weight size is only 16.7 Mb with 4.7 Mb smaller than that of YOLOv8s, meeting the real-time requirements for the picking robot. Furthermore, according to the heat map, our proposed model can focus more on and learn the high-level features of the target apples, and recognize the smaller target apples better than the original YOLOv5s model. Then, in other apple orchard tests, the model can detect the pickable apples in real time and correctly, illustrating a decent generalization ability. |
format | article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2889481127</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2889481127</sourcerecordid><originalsourceid>FETCH-proquest_journals_28894811273</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTwivT38S8zLdZ1crZScMxTyMwtKMovS01RgIknJRYDebmpJRn5KQpp-UUKRamJObolmbmpCokFBTmpCimpJanJJZn5eTwMrGmJOcWpvFCam0HZzTXE2UMXaGJhaWpxSXxWfmlRHlAq3sjCwtLEwtDQyNyYOFUA0_Y7Ow</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2889481127</pqid></control><display><type>article</type><title>YOLOv5s-BC: An improved YOLOv5s-based method for real-time apple detection</title><source>Publicly Available Content Database</source><creator>Liu, Jingfan ; Liu, Zhaobing</creator><creatorcontrib>Liu, Jingfan ; Liu, Zhaobing</creatorcontrib><description>To address the issues associated with the existing algorithms for the current apple detection, this study proposes an improved YOLOv5s-based method, named YOLOv5s-BC, for real-time apple detection, in which a series of modifications have been introduced. Firstly, a coordinate attention (CA) block has been incorporated into the backbone module to construct a new backbone network. Secondly, the original concatenation operation has been replaced with a bidirectional feature pyramid network (BiFPN) in the neck module. Lastly, a new detection head has been added to the head module, enabling the detection of smaller and more distant targets within the field of view of the robot. The proposed YOLOv5s-BC model was compared to several target detection algorithms, including YOLOv5s, YOLOv4, YOLOv3, SSD, Faster R-CNN (ResNet50), and Faster R-CNN (VGG), with significant improvements of 4.6%, 3.6%, 20.48%, 23.22%, 15.27%, and 15.59% in mAP, respectively. The detection accuracy of the proposed model is also greatly enhanced over the original YOLOv5s model. The model boasts an average detection speed of 0.018 seconds per image, and the weight size is only 16.7 Mb with 4.7 Mb smaller than that of YOLOv8s, meeting the real-time requirements for the picking robot. Furthermore, according to the heat map, our proposed model can focus more on and learn the high-level features of the target apples, and recognize the smaller target apples better than the original YOLOv5s model. Then, in other apple orchard tests, the model can detect the pickable apples in real time and correctly, illustrating a decent generalization ability.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Apples ; Computer networks ; Modules ; Object recognition ; Orchards ; Real time ; Robots ; Target detection</subject><ispartof>arXiv.org, 2023-11</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2889481127?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Liu, Jingfan</creatorcontrib><creatorcontrib>Liu, Zhaobing</creatorcontrib><title>YOLOv5s-BC: An improved YOLOv5s-based method for real-time apple detection</title><title>arXiv.org</title><description>To address the issues associated with the existing algorithms for the current apple detection, this study proposes an improved YOLOv5s-based method, named YOLOv5s-BC, for real-time apple detection, in which a series of modifications have been introduced. Firstly, a coordinate attention (CA) block has been incorporated into the backbone module to construct a new backbone network. Secondly, the original concatenation operation has been replaced with a bidirectional feature pyramid network (BiFPN) in the neck module. Lastly, a new detection head has been added to the head module, enabling the detection of smaller and more distant targets within the field of view of the robot. The proposed YOLOv5s-BC model was compared to several target detection algorithms, including YOLOv5s, YOLOv4, YOLOv3, SSD, Faster R-CNN (ResNet50), and Faster R-CNN (VGG), with significant improvements of 4.6%, 3.6%, 20.48%, 23.22%, 15.27%, and 15.59% in mAP, respectively. The detection accuracy of the proposed model is also greatly enhanced over the original YOLOv5s model. The model boasts an average detection speed of 0.018 seconds per image, and the weight size is only 16.7 Mb with 4.7 Mb smaller than that of YOLOv8s, meeting the real-time requirements for the picking robot. Furthermore, according to the heat map, our proposed model can focus more on and learn the high-level features of the target apples, and recognize the smaller target apples better than the original YOLOv5s model. Then, in other apple orchard tests, the model can detect the pickable apples in real time and correctly, illustrating a decent generalization ability.</description><subject>Algorithms</subject><subject>Apples</subject><subject>Computer networks</subject><subject>Modules</subject><subject>Object recognition</subject><subject>Orchards</subject><subject>Real time</subject><subject>Robots</subject><subject>Target detection</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTwivT38S8zLdZ1crZScMxTyMwtKMovS01RgIknJRYDebmpJRn5KQpp-UUKRamJObolmbmpCokFBTmpCimpJanJJZn5eTwMrGmJOcWpvFCam0HZzTXE2UMXaGJhaWpxSXxWfmlRHlAq3sjCwtLEwtDQyNyYOFUA0_Y7Ow</recordid><startdate>20231110</startdate><enddate>20231110</enddate><creator>Liu, Jingfan</creator><creator>Liu, Zhaobing</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231110</creationdate><title>YOLOv5s-BC: An improved YOLOv5s-based method for real-time apple detection</title><author>Liu, Jingfan ; Liu, Zhaobing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28894811273</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Apples</topic><topic>Computer networks</topic><topic>Modules</topic><topic>Object recognition</topic><topic>Orchards</topic><topic>Real time</topic><topic>Robots</topic><topic>Target detection</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Jingfan</creatorcontrib><creatorcontrib>Liu, Zhaobing</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Jingfan</au><au>Liu, Zhaobing</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>YOLOv5s-BC: An improved YOLOv5s-based method for real-time apple detection</atitle><jtitle>arXiv.org</jtitle><date>2023-11-10</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>To address the issues associated with the existing algorithms for the current apple detection, this study proposes an improved YOLOv5s-based method, named YOLOv5s-BC, for real-time apple detection, in which a series of modifications have been introduced. Firstly, a coordinate attention (CA) block has been incorporated into the backbone module to construct a new backbone network. Secondly, the original concatenation operation has been replaced with a bidirectional feature pyramid network (BiFPN) in the neck module. Lastly, a new detection head has been added to the head module, enabling the detection of smaller and more distant targets within the field of view of the robot. The proposed YOLOv5s-BC model was compared to several target detection algorithms, including YOLOv5s, YOLOv4, YOLOv3, SSD, Faster R-CNN (ResNet50), and Faster R-CNN (VGG), with significant improvements of 4.6%, 3.6%, 20.48%, 23.22%, 15.27%, and 15.59% in mAP, respectively. The detection accuracy of the proposed model is also greatly enhanced over the original YOLOv5s model. The model boasts an average detection speed of 0.018 seconds per image, and the weight size is only 16.7 Mb with 4.7 Mb smaller than that of YOLOv8s, meeting the real-time requirements for the picking robot. Furthermore, according to the heat map, our proposed model can focus more on and learn the high-level features of the target apples, and recognize the smaller target apples better than the original YOLOv5s model. Then, in other apple orchard tests, the model can detect the pickable apples in real time and correctly, illustrating a decent generalization ability.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2023-11 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2889481127 |
source | Publicly Available Content Database |
subjects | Algorithms Apples Computer networks Modules Object recognition Orchards Real time Robots Target detection |
title | YOLOv5s-BC: An improved YOLOv5s-based method for real-time apple detection |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T15%3A29%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=YOLOv5s-BC:%20An%20improved%20YOLOv5s-based%20method%20for%20real-time%20apple%20detection&rft.jtitle=arXiv.org&rft.au=Liu,%20Jingfan&rft.date=2023-11-10&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2889481127%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_28894811273%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2889481127&rft_id=info:pmid/&rfr_iscdi=true |