Traffic Sign Recognition Method Based on Dual-Channel CNN

Aiming at traffic sign problem, the traditional LeNet-5 network structure has low accuracy of traffic sign recognition, slow identification speed and ignores natural factors such as weather. A convolutional network structure model with two-channel and multi-scale based on LeNet-5 improvement is prop...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2021 IEEE 15th International Conference on Electronic Measurement & Instruments (ICEMI) s. 364 - 369
Hlavní autori: Zhao, Zeyi, Zhou, Fuqiang, Wang, Shaohong, Xu, Xiaoli, Chao, Fenjin, Lin, Zhoupeng
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 29.10.2021
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Aiming at traffic sign problem, the traditional LeNet-5 network structure has low accuracy of traffic sign recognition, slow identification speed and ignores natural factors such as weather. A convolutional network structure model with two-channel and multi-scale based on LeNet-5 improvement is proposed by convolutional neural network technology. In the dual-channel structure, each channel contains two branching structure, and the number of convolution and image scale of each channel is different, making the feature extraction of different image scales richer. Secondly, the improved network structure greatly increases the number of convolutional kernels compared to the traditional LeNet-5 network structure. Finally, by changing the Sigmoid activation function to the ReLu activation function, changing the stochastic gradient descent algorithm to the Adam algorithm, and adding Dropout layers to prevent overfitting and setting the learning rate, thus increasing the traffic sign recognition rate. The recognition rate of the improved network is 98.6%, floating by 0.5%, relative to the traditional LeNet-5 network structure, the recognition rate increases by more than 15%, verifying that the improved network structure has a certain robustness.
AbstractList Aiming at traffic sign problem, the traditional LeNet-5 network structure has low accuracy of traffic sign recognition, slow identification speed and ignores natural factors such as weather. A convolutional network structure model with two-channel and multi-scale based on LeNet-5 improvement is proposed by convolutional neural network technology. In the dual-channel structure, each channel contains two branching structure, and the number of convolution and image scale of each channel is different, making the feature extraction of different image scales richer. Secondly, the improved network structure greatly increases the number of convolutional kernels compared to the traditional LeNet-5 network structure. Finally, by changing the Sigmoid activation function to the ReLu activation function, changing the stochastic gradient descent algorithm to the Adam algorithm, and adding Dropout layers to prevent overfitting and setting the learning rate, thus increasing the traffic sign recognition rate. The recognition rate of the improved network is 98.6%, floating by 0.5%, relative to the traditional LeNet-5 network structure, the recognition rate increases by more than 15%, verifying that the improved network structure has a certain robustness.
Author Zhou, Fuqiang
Wang, Shaohong
Lin, Zhoupeng
Zhao, Zeyi
Xu, Xiaoli
Chao, Fenjin
Author_xml – sequence: 1
  givenname: Zeyi
  surname: Zhao
  fullname: Zhao, Zeyi
  email: 741259378@qq.com
  organization: Beijing Information Science&Technology University,Ministry of Education, Key Laboratory of Modern Measurement & Control Technology,Beijing,China
– sequence: 2
  givenname: Fuqiang
  surname: Zhou
  fullname: Zhou, Fuqiang
  email: fuqiangzhou@126.com
  organization: Beijing Information Science&Technology University,Ministry of Education, Key Laboratory of Modern Measurement & Control Technology,Beijing,China
– sequence: 3
  givenname: Shaohong
  surname: Wang
  fullname: Wang, Shaohong
  email: wangsh78@126.com
  organization: Beijing Information Science&Technology University,Ministry of Education, Key Laboratory of Modern Measurement & Control Technology,Beijing,China
– sequence: 4
  givenname: Xiaoli
  surname: Xu
  fullname: Xu, Xiaoli
  email: xuxiaoli@bistu.edu.cn
  organization: Beijing Information Science&Technology University,Ministry of Education, Key Laboratory of Modern Measurement & Control Technology,Beijing,China
– sequence: 5
  givenname: Fenjin
  surname: Chao
  fullname: Chao, Fenjin
  email: 760562096@qq.com
  organization: Beijing Information Science&Technology University,Ministry of Education, Key Laboratory of Modern Measurement & Control Technology,Beijing,China
– sequence: 6
  givenname: Zhoupeng
  surname: Lin
  fullname: Lin, Zhoupeng
  email: luperlin@outlook.com
  organization: Beijing Information Science&Technology University,Ministry of Education, Key Laboratory of Modern Measurement & Control Technology,Beijing,China
BookMark eNotj8tKw0AUQEfQhdZ-gQvnBxJzM8-71Fg10FbQui7zuNMOxImkdeHfK9jV4WwOnCt2XsZCjN1CUwM0eNd3i1WvWpS6bpsWatQGFYozNkdjQWslpURoLhluJpdSDvw97wp_ozDuSj7msfAVHfdj5A_uQJH_-eO3G6pu70qhgXfr9TW7SG440PzEGft4Wmy6l2r5-tx398sqA9hjhRpARrTkydgASrZBJPBRmOStjF6TFxhiiCIpl3TQHkPQ6KMSxhnrxIzd_HczEW2_pvzppp_taUj8AmsnRUc
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICEMI52946.2021.9679593
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781665444910
1665444916
EndPage 369
ExternalDocumentID 9679593
Genre orig-research
GrantInformation_xml – fundername: Beijing Information Science&Technology University
  funderid: 10.13039/501100010818
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i118t-96114d98ebe78c1542c3f1bd37fb84db6eb39cdcd3f5af6c6b9cc69bd537a78a3
IEDL.DBID RIE
IngestDate Thu Jun 29 18:37:44 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-96114d98ebe78c1542c3f1bd37fb84db6eb39cdcd3f5af6c6b9cc69bd537a78a3
PageCount 6
ParticipantIDs ieee_primary_9679593
PublicationCentury 2000
PublicationDate 2021-Oct.-29
PublicationDateYYYYMMDD 2021-10-29
PublicationDate_xml – month: 10
  year: 2021
  text: 2021-Oct.-29
  day: 29
PublicationDecade 2020
PublicationTitle 2021 IEEE 15th International Conference on Electronic Measurement & Instruments (ICEMI)
PublicationTitleAbbrev ICEMI
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.7744282
Snippet Aiming at traffic sign problem, the traditional LeNet-5 network structure has low accuracy of traffic sign recognition, slow identification speed and ignores...
SourceID ieee
SourceType Publisher
StartPage 364
SubjectTerms convolutional neural network
Convolutional neural networks
Feature extraction
Instruments
LeNet-5 network structure
Neural networks
Robustness
Stochastic processes
traffic sign recognition
Training
Title Traffic Sign Recognition Method Based on Dual-Channel CNN
URI https://ieeexplore.ieee.org/document/9679593
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7a4sGTSiu-ycGjaTf7yONqtSjoUnzRW8ljIgXZSm39_SbbtSJ48ZaEhGQmkMkk3zcDcO4salZIS7VjjuZe5VRapimaJAwJ_kFRs95f7kRZyslEjVtwseHCIGINPsN-LNZ_-W5uV_GpbKB4zIydtaEtBF9ztRrIFkvU4HYYVl6kKo_Ig5T1m96_0qbUVmO087_5dqH3Q78j441h2YMWVl1QwarEcA_kcfZakYdv3M-8Ivd1EmhyGeyRI6F-tdJvNLIGKnwjw7LswfPo-ml4Q5u8B3QWrvtLqnhwUpySQVkiKK7IU5t5ZlwmvJG5Mzw4wMo66zJfaM8tN8parowrMqGF1Nk-dKp5hQdAbCJRhwu0S5nJffTlMMmE8SlKr6XEQ-hGsafv69AW00bio7-bj2E7ajYe3ak6gc5yscJT2LKfy9nH4qzejy9Ado5s
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmuhJDRjf9uDRwrbb3W2vogYibIii4Ub6NCRkMQj-fttlxZh48dY2bdqZJp1O-30zANdGW0kSrrE0xGDmBMNcE4mtivwQ7x8kJev9tZ_lOR-PxbAGNxsujLW2BJ_ZViiWf_lmrlfhqawt0pAZO96C7YQxGq3ZWhVoi0Si3ev4tSdUsIA9oKRV9f-VOKW0Gw_7_5vxAJo_BDw03JiWQ6jZogHC25UQ8AE9T98K9PSN_JkXaFCmgUa33iIZ5Ot3KznDgTdQ2Bnq5HkTXh7uR50urjIf4Km_8C-xSL2bYgT36sq86hJGdeyIMnHmFGdGpd4FFtpoE7tEulSnSmidCmWSOJMZl_ER1It5YY8B6Yhb6a_QhhLFXPDmbBRnylHLneTcnkAjiD15Xwe3mFQSn_7dfAW73dGgP-n38scz2AtaDgc5FedQXy5W9gJ29Ody-rG4LPfmC9rvkbM
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%3Abook&rft.genre=proceeding&rft.title=2021+IEEE+15th+International+Conference+on+Electronic+Measurement+%26+Instruments+%28ICEMI%29&rft.atitle=Traffic+Sign+Recognition+Method+Based+on+Dual-Channel+CNN&rft.au=Zhao%2C+Zeyi&rft.au=Zhou%2C+Fuqiang&rft.au=Wang%2C+Shaohong&rft.au=Xu%2C+Xiaoli&rft.date=2021-10-29&rft.pub=IEEE&rft.spage=364&rft.epage=369&rft_id=info:doi/10.1109%2FICEMI52946.2021.9679593&rft.externalDocID=9679593