改进YOLOv7-Tiny农田环境下甜椒果实检测

TP391.41; 针对在农田环境下甜椒果实的深度学习目标检测算法容易出现误检率较高、检测精度较低的问题,为提高农业生产管理系统以及农业机器人生产效率.基于YOLOv7-Tiny目标检测算法进行一系列改进.在YOLOv7-Tiny的主干中添加DBB(diverse branch block)模块;在三个输出特征层添加SimAM注意力机制;采用Bi-FPN特征融合机制,并增加跨通道特征融合,在P7层加入ASPP空洞空间卷积池化金字塔结构;采用数据集增强技术,对数据集图片进行扩充和图像处理,将800张甜椒果实数据集图片扩充至4 800张.实验结果表明,在相同实验条件下改进YOLOv7-Tiny相较...

Full description

Saved in:
Bibliographic Details
Published in计算机工程与应用 Vol. 59; no. 15; pp. 329 - 340
Main Authors 赵鹏飞, 钱孟波, 周凯琪, 单奕杰, 吴浩宇
Format Journal Article
LanguageChinese
Published 浙江农林大学 光机电工程学院,杭州 311300 01.08.2023
Subjects
甜椒检测
卷积神经网络
Bi-FPN
bell pepper detection
YOLOv7-Tiny
convolutional neural network
Online AccessGet full text
ISSN1002-8331
DOI10.3778/j.issn.1002-8331.2302-0224

Cover

Abstract TP391.41; 针对在农田环境下甜椒果实的深度学习目标检测算法容易出现误检率较高、检测精度较低的问题,为提高农业生产管理系统以及农业机器人生产效率.基于YOLOv7-Tiny目标检测算法进行一系列改进.在YOLOv7-Tiny的主干中添加DBB(diverse branch block)模块;在三个输出特征层添加SimAM注意力机制;采用Bi-FPN特征融合机制,并增加跨通道特征融合,在P7层加入ASPP空洞空间卷积池化金字塔结构;采用数据集增强技术,对数据集图片进行扩充和图像处理,将800张甜椒果实数据集图片扩充至4 800张.实验结果表明,在相同实验条件下改进YOLOv7-Tiny相较于YOLOv7-Tiny平均准确率(mAP)提高了2.21个百分点,视频检测速度32.82 FPS,改进YOLOv7-Tiny模型体积相较于YOLOv7-Tiny减小5.4 MB.改进YOLOv7-Tiny精度有明显提升,可实现快速、精准检测甜椒果实.
AbstractList TP391.41; 针对在农田环境下甜椒果实的深度学习目标检测算法容易出现误检率较高、检测精度较低的问题,为提高农业生产管理系统以及农业机器人生产效率.基于YOLOv7-Tiny目标检测算法进行一系列改进.在YOLOv7-Tiny的主干中添加DBB(diverse branch block)模块;在三个输出特征层添加SimAM注意力机制;采用Bi-FPN特征融合机制,并增加跨通道特征融合,在P7层加入ASPP空洞空间卷积池化金字塔结构;采用数据集增强技术,对数据集图片进行扩充和图像处理,将800张甜椒果实数据集图片扩充至4 800张.实验结果表明,在相同实验条件下改进YOLOv7-Tiny相较于YOLOv7-Tiny平均准确率(mAP)提高了2.21个百分点,视频检测速度32.82 FPS,改进YOLOv7-Tiny模型体积相较于YOLOv7-Tiny减小5.4 MB.改进YOLOv7-Tiny精度有明显提升,可实现快速、精准检测甜椒果实.
Author 赵鹏飞
吴浩宇
周凯琪
单奕杰
钱孟波
AuthorAffiliation 浙江农林大学 光机电工程学院,杭州 311300
AuthorAffiliation_xml – name: 浙江农林大学 光机电工程学院,杭州 311300
Author_FL QIAN Mengbo
ZHAO Pengfei
SHAN Yijie
ZHOU Kaiqi
WU Haoyu
Author_FL_xml – sequence: 1
  fullname: ZHAO Pengfei
– sequence: 2
  fullname: QIAN Mengbo
– sequence: 3
  fullname: ZHOU Kaiqi
– sequence: 4
  fullname: SHAN Yijie
– sequence: 5
  fullname: WU Haoyu
Author_xml – sequence: 1
  fullname: 赵鹏飞
– sequence: 2
  fullname: 钱孟波
– sequence: 3
  fullname: 周凯琪
– sequence: 4
  fullname: 单奕杰
– sequence: 5
  fullname: 吴浩宇
BookMark eNo9jT9Lw0AYh2-oYK39Em4Oie_dm-sloxT_QSBLHZzK3SVXEuQKHirZBMGl4CDZDB3UWV0EnfwyJvFjWFCcfg_P8Pw2SM_ObUbIFgUfhQh3Cj93zvoUgHkhIvUZrggYC3qk_2_XydC5XAGnKLjAqE9YW318f96fJHFyIbxJbsvmpu6q1-72pXm4_npfdFXdPt21y7p5XraPV-3bYpOsGXnqsuHfDsjx_t5kfOjFycHReDf2HIVR4AWQ6ShMtdJc6yADFAqkjOSIZhAaPuJGpSgFKAwlT9HwwHCWqdAoI42WEgdk-7d7Ka2RdjYt5udndvU4LVwx02VZMmBIOWCAP0kAWlA
ClassificationCodes TP391.41
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.3778/j.issn.1002-8331.2302-0224
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
DocumentTitle_FL Improvement of Sweet Pepper Fruit Detection in YOLOv7-Tiny Farming Environment
EndPage 340
ExternalDocumentID jsjgcyyy202315034
GrantInformation_xml – fundername: 浙江省尖兵领雁研发攻关计划项目
  funderid: (2022C02057)
GroupedDBID -0Y
2B.
4A8
5XA
5XJ
92H
92I
93N
ABJNI
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CUBFJ
CW9
PSX
TCJ
TGT
U1G
U5S
ID FETCH-LOGICAL-s1064-40ec98dcbc5cc4e037b0aa9a61e08f565fbd3a70b38a5d3f54f52eb8fbfafcaa3
ISSN 1002-8331
IngestDate Thu May 29 04:10:54 EDT 2025
IsPeerReviewed false
IsScholarly false
Issue 15
Keywords 甜椒检测
卷积神经网络
Bi-FPN
bell pepper detection
YOLOv7-Tiny
convolutional neural network
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1064-40ec98dcbc5cc4e037b0aa9a61e08f565fbd3a70b38a5d3f54f52eb8fbfafcaa3
PageCount 12
ParticipantIDs wanfang_journals_jsjgcyyy202315034
PublicationCentury 2000
PublicationDate 2023-08-01
PublicationDateYYYYMMDD 2023-08-01
PublicationDate_xml – month: 08
  year: 2023
  text: 2023-08-01
  day: 01
PublicationDecade 2020
PublicationTitle 计算机工程与应用
PublicationTitle_FL Computer Engineering and Applications
PublicationYear 2023
Publisher 浙江农林大学 光机电工程学院,杭州 311300
Publisher_xml – name: 浙江农林大学 光机电工程学院,杭州 311300
SSID ssib051375739
ssib001102935
ssj0000561668
ssib023646291
ssib057620132
Score 1.9761962
Snippet TP391.41; 针对在农田环境下甜椒果实的深度学习目标检测算法容易出现误检率较高、检测精度较低的问题,为提高农业生产管理系统以及农业机器人生产效率.基于YOLOv7-Tiny目标...
SourceID wanfang
SourceType Aggregation Database
StartPage 329
Title 改进YOLOv7-Tiny农田环境下甜椒果实检测
URI https://d.wanfangdata.com.cn/periodical/jsjgcyyy202315034
Volume 59
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVEBS
  databaseName: Inspec with Full Text
  issn: 1002-8331
  databaseCode: ADMLS
  dateStart: 20200501
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text
  omitProxy: false
  ssIdentifier: ssib057620132
  providerName: EBSCOhost
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3LahRBsInJRQ_iE98EsU9h4sz09Os4s-klSGIOJhBPYXoe0RxWMFHYnBTBS8CD5GbIQT2rF0FP_ozZ-BlW9bQ7g0aIwjIU3TX13N6qnu2qIeQWz7lVWtoANxxBUhUK1lwhA8mi2Coe2khgcfLiXTG_ktxZ5asTJ553q0u27GyxfWRdyf94FcbAr1gl-w-eHROFAYDBv3AFD8P1WD6mRlCd0ExTo2jWpzq7v7Sw9FQGyw8HQ2o4VTDfo0Y6rBABZWjax6k0popRA-OKqszjILKgKQCxo23cCCAbhHGK4dEIADIgnnUzWxQB0NIISSG-dBR6NEuRQgaD3E017Bq-xk2lyLoRIB2frHUqcfwYjRqqPgLAX5sWRaOgWeREnKO67yRjoFuLwqmOkClaQzrdgVFI07SLouBm7qhwB4Dgc2Cw7iORmI0P5DVfYm8FrR0QOe5jize2k44kaCW9hKmYcUjw0R3zNP7hR9nJ3-ZU1ei0uOfFg_EGX5sZFuH_hZ0A4yLQryo1H4F8T3S_0ngnnjD_OKhJTVjT2er3qMekVC7qIYfZMQc84x8HmKO1sX58AnNjc2O9GA6HaD7YE7DkBJmKITCGk2QqnVtcuNfm1JCC6janxhcOiLhtsMQjJrlsW8tyJOLbgfoG-yISviTVS9Y0_0Wxb_9daFdFN6jzwXon4Vs-Q077ndp02iy7s2Ri-8E5cqrTv_M8iUe7X398e9NZdAcv9w53Px2--njw9sX3LzuHu3uj969H-3sHH_ZH756NPu9cICt9s9ybD_xLSILNCNL1IAmrQquysAUviqQKmbRhnutcRFWoatgO1bZkuQwtUzkvWc2TmseVVbWt87rIc3aRTA4eDapLZDqvQxHKUsdhKZJKSS1EDKZlMhS5LaPyMrnpNV7zPzKba3_46cpxkK6Sk-26uEYmtx4_qa5D8rxlb3j3_gTg0Y22
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E6%94%B9%E8%BF%9BYOLOv7-Tiny%E5%86%9C%E7%94%B0%E7%8E%AF%E5%A2%83%E4%B8%8B%E7%94%9C%E6%A4%92%E6%9E%9C%E5%AE%9E%E6%A3%80%E6%B5%8B&rft.jtitle=%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%B7%A5%E7%A8%8B%E4%B8%8E%E5%BA%94%E7%94%A8&rft.au=%E8%B5%B5%E9%B9%8F%E9%A3%9E&rft.au=%E9%92%B1%E5%AD%9F%E6%B3%A2&rft.au=%E5%91%A8%E5%87%AF%E7%90%AA&rft.au=%E5%8D%95%E5%A5%95%E6%9D%B0&rft.date=2023-08-01&rft.pub=%E6%B5%99%E6%B1%9F%E5%86%9C%E6%9E%97%E5%A4%A7%E5%AD%A6+%E5%85%89%E6%9C%BA%E7%94%B5%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E6%9D%AD%E5%B7%9E+311300&rft.issn=1002-8331&rft.volume=59&rft.issue=15&rft.spage=329&rft.epage=340&rft_id=info:doi/10.3778%2Fj.issn.1002-8331.2302-0224&rft.externalDocID=jsjgcyyy202315034
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjsjgcyyy%2Fjsjgcyyy.jpg