Design of National Sports Action Feature Extraction System Based on Convolutional Neural Network
Human action recognition is one of the hotspots in computer vision research. Its purpose is to detect and recognize target actions from videos, so that computer systems can understand human actions, and thus it has great research significance. Based on the action features of famous sports, this pape...
Uložené v:
| Vydané v: | Scientific programming Ročník 2022; s. 1 - 10 |
|---|---|
| Hlavný autor: | |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
New York
Hindawi
25.02.2022
John Wiley & Sons, Inc |
| Predmet: | |
| ISSN: | 1058-9244, 1875-919X |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Human action recognition is one of the hotspots in computer vision research. Its purpose is to detect and recognize target actions from videos, so that computer systems can understand human actions, and thus it has great research significance. Based on the action features of famous sports, this paper proposes an action recognition scheme based on RGB-D video compression to establish action features and deep learning as a means of recognition. By establishing the connection between the bone data of the three-dimensional data type and the depth image data, the depth sequence is analyzed and expressed as a three-level structure diagram sequence, which is the overall figure sequence, partial figure sequence, and joint point figure sequence, and then passes through the two-way pool. The sorting algorithm extracts the action features in the three picture sequences and compresses and generates three types of structured images of the corresponding picture sequences, and these three types of structured images are used as the feature expression of the video. When constructing a three-level structure diagram sequence, the innovation of this paper is to splice the extracted key unit image blocks to obtain a three-level structured moving image based on the three-key unit splicing, so that the image is not only retained. In addition to time-space information, the structure information of the depth image is also strengthened, and the amount of calculation is reduced at the same time. Finally, the three types of structured images are input into the convolutional neural network, respectively, and the judgment and recognition results obtained are multiplicatively fused to obtain the final recognition rate of the action. |
|---|---|
| AbstractList | Human action recognition is one of the hotspots in computer vision research. Its purpose is to detect and recognize target actions from videos, so that computer systems can understand human actions, and thus it has great research significance. Based on the action features of famous sports, this paper proposes an action recognition scheme based on RGB-D video compression to establish action features and deep learning as a means of recognition. By establishing the connection between the bone data of the three-dimensional data type and the depth image data, the depth sequence is analyzed and expressed as a three-level structure diagram sequence, which is the overall figure sequence, partial figure sequence, and joint point figure sequence, and then passes through the two-way pool. The sorting algorithm extracts the action features in the three picture sequences and compresses and generates three types of structured images of the corresponding picture sequences, and these three types of structured images are used as the feature expression of the video. When constructing a three-level structure diagram sequence, the innovation of this paper is to splice the extracted key unit image blocks to obtain a three-level structured moving image based on the three-key unit splicing, so that the image is not only retained. In addition to time-space information, the structure information of the depth image is also strengthened, and the amount of calculation is reduced at the same time. Finally, the three types of structured images are input into the convolutional neural network, respectively, and the judgment and recognition results obtained are multiplicatively fused to obtain the final recognition rate of the action. |
| Author | Pang, Yajun |
| Author_xml | – sequence: 1 givenname: Yajun orcidid: 0000-0002-4752-1036 surname: Pang fullname: Pang, Yajun organization: College of Physical Education Luoyang Institute of Science and Technology Luoyang Henan 471023 China lit.edu.cn |
| BookMark | eNp9kEtPwkAUhScGEwHd-QOauNTKTKfz6BIR1ITgAk3c1en0VovQwZmpyL-3UFYmurqPfOfmntNDncpUgNA5wdeEMDaIcBQNmIgFj8UR6hIpWJiQ5KXT9JjJMIni-AT1nFtgTCTBuIteb8GVb1VgimCmfGkqtQzma2O9C4Z6NwcTUL62EIy_vVXtar51HlbBjXKQB808MtWXWdYH-Qxquy9-Y-zHKTou1NLB2aH20fNk_DS6D6ePdw-j4TTUlAof5pJTyQnlBW8-JpRxTWUGSmNQFETWWIoSlgDnGuI4kxI441leCA15LrWmfXTR3l1b81mD8-nC1Lb5x6URp5ywSMS4oaKW0tY4Z6FIden3vhtz5TIlON0lme6STA9JNqKrX6K1LVfKbv_CL1v8vaxytSn_p38A0xSDTQ |
| CitedBy_id | crossref_primary_10_3389_fnbot_2024_1453061 |
| Cites_doi | 10.1007/s10040-016-1478-8 10.1016/j.compeleceng.2020.106719 10.1162/tacl_a_00065 10.3390/app9112331 10.1371/journal.pone.0184191 10.3390/ijgi9030139 10.1016/j.ejor.2018.04.051 10.1080/15568318.2012.740147 10.1186/s13007-019-0443-7 10.1016/j.istruc.2021.02.035 10.1016/j.knosys.2016.07.036 10.3390/app9102036 10.1016/j.aap.2017.05.025 10.1186/s13321-019-0341-z 10.1016/j.trb.2018.04.003 10.1007/s10072-019-03853-z 10.1016/j.ejor.2015.05.039 10.1016/j.eswa.2009.06.048 10.3390/info11040201 10.1007/s10590-019-09236-7 10.3390/app10061967 10.1007/s41019-019-0087-7 |
| ContentType | Journal Article |
| Copyright | Copyright © 2022 Yajun Pang. Copyright © 2022 Yajun Pang. This is an open access article distributed under the Creative Commons Attribution License (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. https://creativecommons.org/licenses/by/4.0 |
| Copyright_xml | – notice: Copyright © 2022 Yajun Pang. – notice: Copyright © 2022 Yajun Pang. This is an open access article distributed under the Creative Commons Attribution License (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. https://creativecommons.org/licenses/by/4.0 |
| DBID | RHU RHW RHX AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1155/2022/5747647 |
| DatabaseName | Hindawi Publishing Complete Hindawi Publishing Subscription Journals Hindawi Publishing Open Access CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database CrossRef |
| Database_xml | – sequence: 1 dbid: RHX name: Hindawi Publishing Open Access url: http://www.hindawi.com/journals/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1875-919X |
| Editor | Ding, Baiyuan |
| Editor_xml | – sequence: 1 givenname: Baiyuan surname: Ding fullname: Ding, Baiyuan |
| EndPage | 10 |
| ExternalDocumentID | 10_1155_2022_5747647 |
| GrantInformation_xml | – fundername: Sanmenxia Vocational and Technical College Project grantid: SZYGCCRC-2020-005 – fundername: Science and Technology Projects of Henan Science and Technology grantid: 182102310041 |
| GroupedDBID | .DC 0R~ 24P 4.4 5VS AAFWJ AAJEY ABJNI ACCMX ACGFS ADBBV AENEX ALMA_UNASSIGNED_HOLDINGS ASPBG AVWKF BCNDV DU5 EBS EST ESX H13 HZ~ IOS KQ8 MIO MV1 NGNOM O9- OK1 RHU RHW RHX AAMMB AAYXX AEFGJ AGXDD AIDQK AIDYY ALUQN CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c337t-d86386136f69191356c38beac0ea3e7b7642959e66ce44b88e656bdf7cedd8cc3 |
| IEDL.DBID | RHX |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000778693900004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1058-9244 |
| IngestDate | Fri Jul 25 09:31:07 EDT 2025 Tue Nov 18 22:15:17 EST 2025 Sat Nov 29 04:07:03 EST 2025 Wed Apr 16 06:25:23 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. https://creativecommons.org/licenses/by/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c337t-d86386136f69191356c38beac0ea3e7b7642959e66ce44b88e656bdf7cedd8cc3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-4752-1036 |
| OpenAccessLink | https://dx.doi.org/10.1155/2022/5747647 |
| PQID | 2636152740 |
| PQPubID | 2046410 |
| PageCount | 10 |
| ParticipantIDs | proquest_journals_2636152740 crossref_citationtrail_10_1155_2022_5747647 crossref_primary_10_1155_2022_5747647 hindawi_primary_10_1155_2022_5747647 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-02-25 |
| PublicationDateYYYYMMDD | 2022-02-25 |
| PublicationDate_xml | – month: 02 year: 2022 text: 2022-02-25 day: 25 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | Scientific programming |
| PublicationYear | 2022 |
| Publisher | Hindawi John Wiley & Sons, Inc |
| Publisher_xml | – name: Hindawi – name: John Wiley & Sons, Inc |
| References | 22 23 24 25 M. D. Moreno (16) 2020; 1 28 H. Shao (10) 2019; 6 P. Zhou (26) 2016; 21 Y. Zhou (29) 2017; 39 31 X. Xiao (27) 2018; 5 12 13 J. Arús-Pous (20) 2019; 11 14 15 17 J. Wang (32) 2016; 5 18 19 2 3 4 J. M. Cairney (5) 2020; 159 S. Nakayama (9) 6 7 8 A. Chen (11) 2020; 37 G. Ma (33) 2018; 277 J. Pang (30) 2017; 16 K. He (1) 21 |
| References_xml | – volume: 21 start-page: 512 issue: 5 year: 2016 ident: 26 article-title: Self-organizing map neural network (SOM) downscaling method to simulate daily precipitation in the Yangtze and Huaihe River Basin publication-title: Climatic and Environmental Research – volume: 6 start-page: 173 issue: 3 year: 2019 ident: 10 article-title: A reliability-based stochastic traffic assignment model for network with multiple user classes under uncertainty in demand publication-title: Networks and Spatial Economics – ident: 28 doi: 10.1007/s10040-016-1478-8 – ident: 3 doi: 10.1016/j.compeleceng.2020.106719 – ident: 15 doi: 10.1162/tacl_a_00065 – ident: 23 doi: 10.3390/app9112331 – start-page: 770 ident: 1 article-title: Deep residual learning for image recognition – ident: 7 doi: 10.1371/journal.pone.0184191 – ident: 19 doi: 10.3390/ijgi9030139 – ident: 14 doi: 10.1016/j.ejor.2018.04.051 – ident: 12 doi: 10.1080/15568318.2012.740147 – ident: 21 doi: 10.1186/s13007-019-0443-7 – volume: 277 start-page: 141 issue: 7 year: 2018 ident: 33 article-title: Research on the design of juvenile football players' sports injury prediction model publication-title: Automation Technology and Application – volume: 1 start-page: 1 issue: 2 year: 2020 ident: 16 article-title: Translation quality gained through the implementation of the iso en 17100:2015 and the usage of the blockchain publication-title: Babel – ident: 8 doi: 10.1016/j.istruc.2021.02.035 – ident: 6 doi: 10.1016/j.knosys.2016.07.036 – ident: 24 doi: 10.3390/app9102036 – volume: 5 start-page: 216 issue: 12 year: 2018 ident: 27 article-title: Analysis on the employment psychological problems and adjustment of retired athletes in the process of career transformation publication-title: Modern Vocational Education – volume: 16 start-page: 74 issue: 1 year: 2017 ident: 30 article-title: Research on the evaluation model of sports training adaptation based on self-organizing neural network publication-title: Journal of Nanjing Institute of Physical Education – volume: 39 start-page: 95 issue: 1 year: 2017 ident: 29 article-title: Sports video athlete detection using convolutional neural network publication-title: Journal of Natural Science of Xiangtan University – ident: 2 doi: 10.1016/j.aap.2017.05.025 – volume: 11 start-page: 20 issue: 1 year: 2019 ident: 20 article-title: Exploring the GDB-13 chemical space using deep generative models publication-title: Journal of Cheminformatics doi: 10.1186/s13321-019-0341-z – ident: 4 doi: 10.1016/j.trb.2018.04.003 – ident: 31 doi: 10.1007/s10072-019-03853-z – ident: 13 doi: 10.1016/j.ejor.2015.05.039 – volume: 37 start-page: 1608 issue: 2 year: 2020 ident: 11 article-title: Stochastic multi-objective models for network design problem publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2009.06.048 – ident: 9 article-title: Traffic network equilibrium model for uncertain demands – ident: 17 doi: 10.3390/info11040201 – volume: 5 start-page: 352 issue: 4 year: 2016 ident: 32 article-title: Correlation analysis between injuries and functional movement screening for athletes of the National Shooting Team publication-title: Journal of Capital Institute of Physical Education – ident: 22 doi: 10.1007/s10590-019-09236-7 – ident: 18 doi: 10.3390/app10061967 – volume: 159 start-page: 324 issue: 1 year: 2020 ident: 5 article-title: Mining information from atom probe data publication-title: Ultramicroscopy – ident: 25 doi: 10.1007/s41019-019-0087-7 |
| SSID | ssj0018100 |
| Score | 2.2455068 |
| Snippet | Human action recognition is one of the hotspots in computer vision research. Its purpose is to detect and recognize target actions from videos, so that... |
| SourceID | proquest crossref hindawi |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | Algorithms Artificial neural networks Big Data Classification Computer vision Datasets Deep learning Feature extraction Human activity recognition Human motion Image retrieval Machine learning Neural networks Sorting algorithms Splicing Sports Target detection Video compression |
| Title | Design of National Sports Action Feature Extraction System Based on Convolutional Neural Network |
| URI | https://dx.doi.org/10.1155/2022/5747647 https://www.proquest.com/docview/2636152740 |
| Volume | 2022 |
| WOSCitedRecordID | wos000778693900004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVWIB databaseName: Wiley Online Library Open Access (WRLC) customDbUrl: eissn: 1875-919X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0018100 issn: 1058-9244 databaseCode: 24P dateStart: 19920101 isFulltext: true titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3dS8MwEA9uKPjitzidIw_zSQpb89nHOTf2NIYo7K22aYqD0UnbTf98L2k60CH6VFIuhd7lcnfc3e8Q6voiigPua08QrT3apxHoHOEeAV9ekCgmjFbDJsR0KufzYOZAkordFD5YOxOe-xC3U8GpaKCGZKZy62ky3yYLZL9XgQ4w0F0wV3V9-4-93yzPwZsJeT8WO1ewtSvjE3TkHEI8qCR4ivZ0doaO62EL2OneOXp9tLUWeJVih2W9xHZEeYEHtjcBG29unWs8-izzql0BV3jk-AFMVYJhPVxlG3fWYLsB5rAPWwl-gV7Go-fhxHPjETxFiCi9RILugDXmKQ8g6iKMKyJjuEh7OiJaxPDPfsACzbnSlMZSavDd4iQVSieJVIpcoma2yvQVwgklXAEjg8gkOlMV-zGXWlNuwIDgdQvd16wLlcMONyMslqGNIRgLDaNDx-gWuttSv1eYGb_QdZ0U_iBr1yIKnYIVoc8JNxN5ae_6f1-5QYdmabvRWRs1y3ytb9G-2pSLIu-ghk9nHXusvgC2OcLF |
| linkProvider | Hindawi Publishing |
| 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=Design+of+National+Sports+Action+Feature+Extraction+System+Based+on+Convolutional+Neural+Network&rft.jtitle=Scientific+programming&rft.au=Pang%2C+Yajun&rft.date=2022-02-25&rft.pub=Hindawi&rft.issn=1058-9244&rft.eissn=1875-919X&rft.volume=2022&rft_id=info:doi/10.1155%2F2022%2F5747647&rft.externalDocID=10_1155_2022_5747647 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1058-9244&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1058-9244&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1058-9244&client=summon |