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...
Uloženo v:
| Vydáno v: | 2021 IEEE 15th International Conference on Electronic Measurement & Instruments (ICEMI) s. 364 - 369 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
29.10.2021
|
| Témata: | |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| 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 Xplore IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) 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 | 1.774528 |
| 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/eLvHCXMwlV1LSwMxEA5t8eBJpRXf5ODRtJtkN4-r1aIHl-IDeitJJpFC2Uof_n6T7VoRvHhLhoEkE5hHMjMfQtepowsLtCCZCIHkEihRJs-IyXOw3IBWHmqwCVmWajLR4xa62dXCeO_r5DPfT8P6Lx8WbpOeygZaJGRs3kZtKcW2VqtJ2aKZHjwO484LpvOUecBov-H-BZtSW43Rwf_WO0S9n_I7PN4ZliPU8lUX6WhVUrsH_DJ7r_Dzd97PosJPNQg0vo32CHCc323MnKSqgcrP8bAse-htdP86fCAN7gGZRXd_TbSIQUqSkvVSuejjMMcDtcBlsCqKUMQAWDtwwENhgnDCaueEtlBwaaQy_Bh1qkXlTxDOLDgRyYpyyIFlNrJ5GjQIZqMadKeom449_di2tpg2Jz77m3yO9pNkk-pm-gJ11suNv0R77nM9Wy2v6vv4Ap20jW8 |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5qFfSk0opvc_Bo2t0km91crZYW26Vohd5KnlIoW6mtv99ku1YEL96SYSDJBOaRzMwHcBs6uhAXJzjizmGWmhhnkkVYMmYUlUZk1pRgE2meZ5OJGNXgblsLY60tk89sKwzLv3yz0OvwVNYWPCBj0x3YTRgj0aZaq0raiiPR7nf83hMiWMg9IHGr4v8FnFLaje7h_1Y8guZPAR4abU3LMdRs0QDh7Upo-IBeZm8Fev7O_FkUaFjCQKN7b5EM8vOHtZzjUDdQ2Dnq5HkTXruP404PV8gHeOYd_hUW3IcpQU7Kppn2Xg7R1MXK0NSpzAuR-xBYaKMNdYl0XHMltOZCmYSmMs0kPYF6sSjsKaBIGc09OYupYYZEyrPZ2AnDifKKUJ9BIxx7-r5pbjGtTnz-N_kG9nvj4WA66OdPF3AQpBwUORGXUF8t1_YK9vTnavaxvC7v5gsq1JC2 |
| 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 |