Neural networks modification for solving the traffic signs detection problem
The paper deals with the implementation of the traffic signs detection model on the deep neural network basis. The complexity of the problem lies in the detected objects size. The paper considers the use of modern approaches to the deep neural networks Mobile Net v2 and Tiny YOLO v3 implementation t...
Saved in:
| Published in | IOP conference series. Materials Science and Engineering Vol. 695; no. 1; pp. 12024 - 12029 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
Bristol
IOP Publishing
01.11.2019
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | The paper deals with the implementation of the traffic signs detection model on the deep neural network basis. The complexity of the problem lies in the detected objects size. The paper considers the use of modern approaches to the deep neural networks Mobile Net v2 and Tiny YOLO v3 implementation to solve the detection problem in real time. Also, a modification of the considered networks is proposed, which allows increasing the Average Precision index by more than 20%. For the networks training GPGPU NVIDIA 1080 and a signs images set called Russian traffic sign images dataset - RTSD which includes more than 15,000 frames for training and more than 3,000 frames for carrying out testing were used. |
|---|---|
| AbstractList | The paper deals with the implementation of the traffic signs detection model on the deep neural network basis. The complexity of the problem lies in the detected objects size. The paper considers the use of modern approaches to the deep neural networks Mobile Net v2 and Tiny YOLO v3 implementation to solve the detection problem in real time. Also, a modification of the considered networks is proposed, which allows increasing the Average Precision index by more than 20%. For the networks training GPGPU NVIDIA 1080 and a signs images set called Russian traffic sign images dataset - RTSD which includes more than 15,000 frames for training and more than 3,000 frames for carrying out testing were used. Abstract The paper deals with the implementation of the traffic signs detection model on the deep neural network basis. The complexity of the problem lies in the detected objects size. The paper considers the use of modern approaches to the deep neural networks Mobile Net v2 and Tiny YOLO v3 implementation to solve the detection problem in real time. Also, a modification of the considered networks is proposed, which allows increasing the Average Precision index by more than 20%. For the networks training GPGPU NVIDIA 1080 and a signs images set called Russian traffic sign images dataset - RTSD which includes more than 15,000 frames for training and more than 3,000 frames for carrying out testing were used. |
| Author | Filatov, D. M. Devyatkin, A.V. |
| Author_xml | – sequence: 1 givenname: A.V. surname: Devyatkin fullname: Devyatkin, A.V. email: avdevyatkin@etu.ru organization: Department of ACS, SPbSETU "LETI" , Russia – sequence: 2 givenname: D. M. surname: Filatov fullname: Filatov, D. M. email: dmfilatov@etu.ru organization: Department of ACS, SPbSETU "LETI" , Russia |
| BookMark | eNqFkE9LxDAQxYOs4O7qV5CAFy-1mbRJ2qMs6x9Y9aCCt9BtkjVrt6lJV_Hb21pZEQRPM8y8N2_4TdCodrVG6BjIGZAsi0EwEWV5_hTznMUQE6CEpntovFuMdn0GB2gSwpoQLtKUjNHiVm99UeFat-_OvwS8ccoaWxatdTU2zuPgqjdbr3D7rHHrC9MtcbCrOmClW11-6RrvlpXeHKJ9U1RBH33XKXq8mD_MrqLF3eX17HwRlZTnaaSzhKgcGCTMiO5XJZISWKFLJvqhTljBGWMmIUCEWDJqhMoVBZ6VzBDFkyk6Ge52ua9bHVq5dltfd5GSMg6MArCsU_FBVXoXgtdGNt5uCv8hgcienOyhyB6Q7MhJkAO5zkgHo3XNz-V_Tad_mG7u579kslEm-QR4Mn51 |
| Cites_doi | 10.1007/978-3-642-21227-7_23 10.1109/CVPR.2018.00474 10.1007/s11263-009-0275-4 10.18287/2412-6179-2016-40-2-294-300 10.1109/ICCV.2015.169 10.1109/ICCV.2017.322 |
| ContentType | Journal Article |
| Copyright | Published under licence by IOP Publishing Ltd 2019. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: Published under licence by IOP Publishing Ltd – notice: 2019. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | O3W TSCCA AAYXX CITATION 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU D1I DWQXO HCIFZ KB. L6V M7S PDBOC PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
| DOI | 10.1088/1757-899X/695/1/012024 |
| DatabaseName | Open Access: IOP Publishing Free Content IOPscience (Open Access) CrossRef ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Materials Science Collection ProQuest Central Korea SciTech Premium Collection (Proquest) (PQ_SDU_P3) https://resources.nclive.org/materials ProQuest Engineering Collection Engineering Database Materials Science Collection Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
| DatabaseTitle | CrossRef Publicly Available Content Database ProQuest Materials Science Collection Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition Materials Science Collection ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection Materials Science Database ProQuest One Academic Engineering Collection |
| DatabaseTitleList | CrossRef Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: O3W name: Open Access: IOP Publishing Free Content url: http://iopscience.iop.org/ sourceTypes: Enrichment Source Publisher – sequence: 2 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| DocumentTitleAlternate | Neural networks modification for solving the traffic signs detection problem |
| EISSN | 1757-899X |
| ExternalDocumentID | 10_1088_1757_899X_695_1_012024 MSE_695_1_012024 |
| GroupedDBID | 1JI 5B3 5PX 5VS AAJIO AAJKP ABHWH ABJCF ACAFW ACGFO ACHIP ACIPV AEFHF AEJGL AFKRA AFYNE AHSEE AIYBF AKPSB ALMA_UNASSIGNED_HOLDINGS ASPBG ATQHT AVWKF AZFZN BENPR BGLVJ CCPQU CEBXE CJUJL CRLBU EBS EDWGO EQZZN GROUPED_DOAJ GX1 HCIFZ HH5 IJHAN IOP IZVLO KB. KNG KQ8 M7S N5L O3W OK1 P2P PDBOC PIMPY PJBAE PTHSS RIN RNS SY9 T37 TR2 TSCCA W28 AAYXX CITATION 8FE 8FG ABUWG AZQEC D1I DWQXO L6V PQEST PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c2694-e830d915135f7202d73c15aec571513e35a6555f301077b52f7d9d2168c5f0d63 |
| IEDL.DBID | BENPR |
| ISSN | 1757-8981 |
| IngestDate | Fri Sep 13 04:46:48 EDT 2024 Fri Aug 23 02:43:20 EDT 2024 Thu Jan 07 13:49:51 EST 2021 Wed Aug 21 03:40:55 EDT 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| License | Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c2694-e830d915135f7202d73c15aec571513e35a6555f301077b52f7d9d2168c5f0d63 |
| OpenAccessLink | https://www.proquest.com/docview/2561521158/abstract/?pq-origsite=%requestingapplication% |
| PQID | 2561521158 |
| PQPubID | 4998670 |
| PageCount | 6 |
| ParticipantIDs | crossref_primary_10_1088_1757_899X_695_1_012024 proquest_journals_2561521158 iop_journals_10_1088_1757_899X_695_1_012024 |
| PublicationCentury | 2000 |
| PublicationDate | 20191101 |
| PublicationDateYYYYMMDD | 2019-11-01 |
| PublicationDate_xml | – month: 11 year: 2019 text: 20191101 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | Bristol |
| PublicationPlace_xml | – name: Bristol |
| PublicationTitle | IOP conference series. Materials Science and Engineering |
| PublicationTitleAlternate | IOP Conf. Ser.: Mater. Sci. Eng |
| PublicationYear | 2019 |
| Publisher | IOP Publishing |
| Publisher_xml | – name: IOP Publishing |
| References | Timofte (MSE_695_1_012024bib9) Everingham (MSE_695_1_012024bib7) 2010; 88 Lin (MSE_695_1_012024bib5) 2016 Sandler (MSE_695_1_012024bib11) 2018 Redmon (MSE_695_1_012024bib2) 2018 MSE_695_1_012024bib8 Girshick (MSE_695_1_012024bib3) 2015 Lin (MSE_695_1_012024bib6) 2014 Shakhuro (MSE_695_1_012024bib12) 2016; 40 He (MSE_695_1_012024bib4) 2017 Liu (MSE_695_1_012024bib1) 2016 Larsson (MSE_695_1_012024bib10) |
| References_xml | – start-page: 238 ident: MSE_695_1_012024bib10 article-title: Using Fourier Descriptors and Spatial Models for Traffic Sign Recognition doi: 10.1007/978-3-642-21227-7_23 contributor: fullname: Larsson – year: 2018 ident: MSE_695_1_012024bib11 article-title: MobileNetV2: Inverted Residuals and Linear Bottlenecks doi: 10.1109/CVPR.2018.00474 contributor: fullname: Sandler – start-page: 21 year: 2016 ident: MSE_695_1_012024bib1 article-title: SSD: Single Shot MultiBox Detector contributor: fullname: Liu – year: 2016 ident: MSE_695_1_012024bib5 article-title: Feature Pyramid Networks for Object Detection contributor: fullname: Lin – volume: 88 start-page: 303 year: 2010 ident: MSE_695_1_012024bib7 article-title: The Pascal Visual Object Classes (VOC) Challenge publication-title: Int. J. Comput. Vision doi: 10.1007/s11263-009-0275-4 contributor: fullname: Everingham – year: 2018 ident: MSE_695_1_012024bib2 article-title: Yolov3: An incremental improvement contributor: fullname: Redmon – start-page: 740 year: 2014 ident: MSE_695_1_012024bib6 article-title: Microsoft COCO: Common Objects in Context contributor: fullname: Lin – volume: 40 start-page: 294 year: 2016 ident: MSE_695_1_012024bib12 article-title: Russian traffic sign images dataset publication-title: Computer Optics doi: 10.18287/2412-6179-2016-40-2-294-300 contributor: fullname: Shakhuro – year: 2015 ident: MSE_695_1_012024bib3 article-title: Fast R-CNN doi: 10.1109/ICCV.2015.169 contributor: fullname: Girshick – ident: MSE_695_1_012024bib8 – ident: MSE_695_1_012024bib9 article-title: Traffic Sign Recognition - How far are we from the solution? contributor: fullname: Timofte – year: 2017 ident: MSE_695_1_012024bib4 article-title: Mask R-CNN doi: 10.1109/ICCV.2017.322 contributor: fullname: He |
| SSID | ssj0067440 |
| Score | 2.1659486 |
| Snippet | The paper deals with the implementation of the traffic signs detection model on the deep neural network basis. The complexity of the problem lies in the... Abstract The paper deals with the implementation of the traffic signs detection model on the deep neural network basis. The complexity of the problem lies in... |
| SourceID | proquest crossref iop |
| SourceType | Aggregation Database Enrichment Source Publisher |
| StartPage | 12024 |
| SubjectTerms | Artificial neural networks deep neural network detection MobileNet Neural networks Object recognition Traffic models Traffic signs Training YOLO |
| SummonAdditionalLinks | – databaseName: Open Access: IOP Publishing Free Content dbid: O3W link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT4MwFG7cvOjB-DNOp6mJN4NQoL-OxmxZjNODLu7WlLbcZMuG_7-vBaKLMcYbgQeUj_a9j_K9V4SunRQu4ZZFMrVJlIeJJpaxyDFmSsMKohOf4Dx9YpNZ_jCnnZow5MIslq3rv4XNplBwA2EriBMxBDxwrFLOYyZpTGKf_pnmPbQNsTf1qr7n7K1zxszXvws5keEcQbok4V-vsxGfetCGH046RJ7xPtprKSO-axp4gLZcdYh2vxUSPEKPvsYG2FSNqHuN3xfWa4AC7Bh4KYYu5qcOMPA9XK-0LxyBvXZjja2rgxyrwu3iMsdoNh693k-idp2EyPg81MiJLLESQndGSw7PYHlmCNXOUO53uoxqRiktYSwnnBc0LbmVNiVMGFomlmUnqF8tKneKMHw8OGlkIXVa5EZQQUpqNbAYXTCTWD5AcYeOWjblMFT4jS2E8ngqj6cCPBVRDZ4DdAMgqnZkrP-0vtqwnr6MNo6rpS0HaNi9kC9DYG6eiRAqzv51w3O0AxRINtmFQ9SvVx_uAmhGXVyGjvQJ5t3EJA priority: 102 providerName: IOP Publishing |
| Title | Neural networks modification for solving the traffic signs detection problem |
| URI | https://iopscience.iop.org/article/10.1088/1757-899X/695/1/012024 https://www.proquest.com/docview/2561521158/abstract/ |
| Volume | 695 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwhV1LT-MwEB7RcoEDYnmILg8ZiRuKEiexY58Qu2opiJd4iN6sxHYkDqRdWv4_M3kIqpV2L5Fiz8Wf7ZnxPAFOvFY-ypwMdOyiIK0NTTKRgZfSllYWPI8owfnmVo6f06uJmKzAuMuFobDKjifWjNpNLdnIQxTNJGq4UGFekBXALsKz2Z-A-keRn7VtptGD1Zin5LBd_TW8vX_ouLKkQnh1cqRArqwV77KF8QHYjulJKLUIeUj5pHG6JKh6r9PZX9y6FkGjTdhodUd23mz2D1jx1Rasf6souA3XVGwDaaomunvO3qaOgoFq_BkqqAzPGtkQGCp-DNdHFSQYBXHMmfOLOi6rYm2XmR14Hg2ffo-DtmFCYCkhNfAqiZxGGZ6IMsM1uCyxXOTeiowGfSJyKYQo8VJHWVaIuMycdjGXyooycjLZhX41rfweMHxFeG11ofO4SK0SipfC5ajO5IW0kcsGEHbomFlTF8PU_mylDOFpCE-DeBpuGjwHcIogmvaKzP9LfbxEffM4XJo3M1cO4KDbkC_Cr3Py89_T-7CGyo9u8goPoL94__CHqGAsiiPoqdHFUXuC8O_y7h6_d8nLJ2Aqy-E |
| link.rule.ids | 315,786,790,12792,21416,27957,27958,33408,33779,38900,38925,43635,43840,53877,53903 |
| linkProvider | ProQuest |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwhV07TwMxDI5oGYAB8RSFAkFiQ6d7JpdMCKGWAm0XWqlbdJfkJAbuSlv-P_Y9VCokWBMv-ZLYjuPPJuTWSmG92HBHBsZzojLQxEPuWM51pnnqJx4SnEdjPphGLzM2qwNuyzqtstGJpaI2hcYYuQumGU2Nz8T9_NPBrlH4u1q30GiR7SgE04lM8f5To4k5Fr8rCZEMNLEUfsMQhkdfPSZnLpfM9V3kkAbRhnFqvRfzXxq6NDv9A7Jf-4v0odrgQ7Jl8yOy96OK4DEZYoENkMmrjO4l_SgMJgCVmFNwSimcL4wbUHD26GqRYNUIiokbS2rsqszFymndWeaETPu9yePAqZskOBpJqI4VoWck2O2QZTGswcSh9lliNYtx0IYs4YyxDC6yF8cpC7LYSBP4XGiWeYaHp6SdF7k9IxReDlZqmcokSCMtmPAzZhJwYZKUa8_EHeI26Kh5VQtDlX_YQijEUyGeCvBUvqrw7JA7AFHV12L5r_TNhvTorbcxr-Ym65BusyFrwfXZOP97-prsDCajoRo-j18vyC44P7LiFXZJe7X4spfgYKzSq_IUfQMg18bF |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLa2ISE4IJ5iMCBI3FDpM2lyRLBpwDaQYGK3qE3SG920jf-P0wcwIYS4Va3bpl8c-0tqOwAXRnDjxZo5ItCeExULTSxkjmFMZYqlfuLZBOfhiPXH0f2EThrQ_cyFmc4q03-Fh2Wh4BLCKiCOu-jw0LAKMXGZoK7v2vTPIHJnOmvCGsU5vFX3x_C1NsjM1sAr8iKL-7hfJwr_-qwVH9XEdvww1IX36W3DVkUbyXXZyB1omHwXNr8VE9yDga2zgTJ5Gdi9IG9TbeOACugJclOCamaXDwhyPrKcJ7Z4BLHxGwuizbIIycpJtcHMPox73ZebvlPtleAom4vqGB56WqD7DmkW4zfoOFQ-TYyisT1pQpowSmmG49mL45QGWayFDnzGFc08zcIDaOXT3BwCwQmEEUqkIgnSSHHK_YzqBJlMkjLl6bgNbo2OnJUlMWTxK5tzafGUFk-JeEpflni24RJBlNXoWPwpfb4iPXzurlyX2NNt6NQd8iWI7M2yEZ_yo3-98AzWn257cnA3ejiGDWREokw27EBrOX83J8g6lulpoVMfRrPIGA |
| 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=Neural+networks+modification+for+solving+the+traffic+signs+detection+problem&rft.jtitle=IOP+conference+series.+Materials+Science+and+Engineering&rft.au=Devyatkin%2C+A+V&rft.au=Filatov%2C+D+M&rft.date=2019-11-01&rft.pub=IOP+Publishing&rft.issn=1757-8981&rft.eissn=1757-899X&rft.volume=695&rft.issue=1&rft_id=info:doi/10.1088%2F1757-899X%2F695%2F1%2F012024 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1757-8981&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1757-8981&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1757-8981&client=summon |