Construction of tennis pose estimation and action recognition model based on improved ST-GCN
With the rapid growth of computer vision and deep learning technologies, the application of pose estimation and action recognition in sports training has become increasingly widespread. Due to factors such as complex movements, fast speed, and limb occlusion, pose estimation and action recognition i...
Gespeichert in:
| Veröffentlicht in: | Molecular & cellular biomechanics Jg. 21; H. 4; S. 605 |
|---|---|
| 1. Verfasser: | |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
06.12.2024
|
| ISSN: | 1556-5297, 1556-5300 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | With the rapid growth of computer vision and deep learning technologies, the application of pose estimation and action recognition in sports training has become increasingly widespread. Due to factors such as complex movements, fast speed, and limb occlusion, pose estimation and action recognition in tennis face significant challenges. Therefore, this study first introduces selective dropout and pyramid region of interest pooling layer strategies in fast region convolutional neural networks. Secondly, a pose estimation algorithm based on multi-scale fusion pose residual network 50 is designed, and finally a spatiotemporal graph convolutional network model is constructed by fusing channel attention module and multi-scale dilated convolution module. The data showed that the average detection accuracy of the improved attitude residual network 50 was 70.4%, and the accuracy of object detection for small, medium, and large objects was 57.4%, 69.3%, and 79.2%, respectively. The continuous action recognition accuracy and inter action fluency detection time of the improved spatiotemporal graph convolutional network were 93.8% and 19.2 ms, respectively. When the sample size was 1000, its memory usage was 1378 MB and the running time was 32.7 ms. Experiments have shown that the improved model achieves high accuracy and robustness in tennis action recognition tasks, especially in complex scenes and limb occlusion conditions, where the model shows significant advantages. This study aims to provide an efficient and accurate motion recognition technology for tennis posture analysis and intelligent training. |
|---|---|
| AbstractList | With the rapid growth of computer vision and deep learning technologies, the application of pose estimation and action recognition in sports training has become increasingly widespread. Due to factors such as complex movements, fast speed, and limb occlusion, pose estimation and action recognition in tennis face significant challenges. Therefore, this study first introduces selective dropout and pyramid region of interest pooling layer strategies in fast region convolutional neural networks. Secondly, a pose estimation algorithm based on multi-scale fusion pose residual network 50 is designed, and finally a spatiotemporal graph convolutional network model is constructed by fusing channel attention module and multi-scale dilated convolution module. The data showed that the average detection accuracy of the improved attitude residual network 50 was 70.4%, and the accuracy of object detection for small, medium, and large objects was 57.4%, 69.3%, and 79.2%, respectively. The continuous action recognition accuracy and inter action fluency detection time of the improved spatiotemporal graph convolutional network were 93.8% and 19.2 ms, respectively. When the sample size was 1000, its memory usage was 1378 MB and the running time was 32.7 ms. Experiments have shown that the improved model achieves high accuracy and robustness in tennis action recognition tasks, especially in complex scenes and limb occlusion conditions, where the model shows significant advantages. This study aims to provide an efficient and accurate motion recognition technology for tennis posture analysis and intelligent training. |
| Author | Yu, Yang |
| Author_xml | – sequence: 1 givenname: Yang surname: Yu fullname: Yu, Yang |
| BookMark | eNo1kMFKxDAQhoOs4O4qvkJunqpJpknsUYruCose7FEo03YilW2yJFXw7S2tnuYb_p9h-DZs5YMnxq6luDXKSHs3tI0R-oytpdYm0yDE6p9VYS_YJqVPIXJZKLtm72XwaYxf7dgHz4PjI3nfJ34KiTilsR9wTtB3HJdSpDZ8-H7mIXR05A0m6vi09sMphu-J36psV75csnOHx0RXf3PLqqfHqtxnh9fdc_lwyFoJWme2QCmdcg0p6iwaLMC2OaK57whdkTfOWgtOACjbCARowBCRA6FQg4Qtu1nOtjGkFMnVpzj9HX9qKerZSb04gV_gKFdL |
| ContentType | Journal Article |
| DBID | AAYXX CITATION |
| DOI | 10.62617/mcb605 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| EISSN | 1556-5300 |
| ExternalDocumentID | 10_62617_mcb605 |
| GroupedDBID | --- 123 AAFWJ AAYXX ADMLS AENEX AFFHD AFKRA ALMA_UNASSIGNED_HOLDINGS BBNVY BENPR BHPHI CCPQU CITATION EBS EJD F5P HCIFZ M7P P2P PHGZM PHGZT PIMPY PQGLB RTS |
| ID | FETCH-LOGICAL-c1355-79a11f2fbe2ed7a6a937c4aa68deaf94bf7773f03327b0a33b36eeef302a5313 |
| ISSN | 1556-5297 |
| IngestDate | Sat Nov 29 02:47:36 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| License | https://creativecommons.org/licenses/by/4.0 |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c1355-79a11f2fbe2ed7a6a937c4aa68deaf94bf7773f03327b0a33b36eeef302a5313 |
| OpenAccessLink | https://doi.org/10.62617/mcb605 |
| ParticipantIDs | crossref_primary_10_62617_mcb605 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-12-06 |
| PublicationDateYYYYMMDD | 2024-12-06 |
| PublicationDate_xml | – month: 12 year: 2024 text: 2024-12-06 day: 06 |
| PublicationDecade | 2020 |
| PublicationTitle | Molecular & cellular biomechanics |
| PublicationYear | 2024 |
| SSID | ssj0041927 |
| Score | 2.3280652 |
| Snippet | With the rapid growth of computer vision and deep learning technologies, the application of pose estimation and action recognition in sports training has... |
| SourceID | crossref |
| SourceType | Index Database |
| StartPage | 605 |
| Title | Construction of tennis pose estimation and action recognition model based on improved ST-GCN |
| Volume | 21 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1556-5300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0041927 issn: 1556-5297 databaseCode: M7P dateStart: 20040101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest - Publicly Available Content Database customDbUrl: eissn: 1556-5300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0041927 issn: 1556-5297 databaseCode: PIMPY dateStart: 20040101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1556-5300 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0041927 issn: 1556-5297 databaseCode: BENPR dateStart: 20040101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtZ3NS8MwFMDDnApexE_8JgdvI9o1bdKeRIYfF8cOPUwQRtImMNBuOB3zv_clabc4D-rBS2lDUkp-4b2X5n0gdK6FTgIZxUSAviER6HSSFFQSXUgdpiIRsXbFJni3m_T7aa_RuKpjYabPvCyT2Swd_ytqaAPYJnT2D7jnL4UGuAfocAXscP0VeFOCs04Kaz0AjP_KpDU2jukmpYaLVXRJWl2nuRMR3NvKOC2j2wpzjjC0_xyMUZqRu07XN2Uf6sK6dvWYAwD7YOP5TTix50b_-G4lvai0ZPWTIbSpDAPmy8WYwZ7VudJeKK-NBoEvTF24c7VoIk8yMhtd_U1iM5MRHqb0JZdVj685sZd01dyDEPYudujADVxBqyHsfALru9mrVbE54bbVdeqvd1HTduClG-iZI55dkW2hzWpDgK8dyG3UUOUOWnclQj920ZOPE480djixwYkXODHgxA4n9nBiixNbnBgea5zY4dxD2e1N1rknVUUMkrfBMCQ8Fe22DrVUoSq4YAKMyzwSgiWFEjqNpOacUx1QGnIZCEolZUopTYNQgLCl-6hZjkp1gHAuTFahNI54HkaFZokWXIM5KqSUinF5CF2qeRmMXd6TwdKcH_3c5RhtLFbTCWrCdKlTtJZP34aT1zPL6hOU508o |
| linkProvider | ProQuest |
| 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=Construction+of+tennis+pose+estimation+and+action+recognition+model+based+on+improved+ST-GCN&rft.jtitle=Molecular+%26+cellular+biomechanics&rft.au=Yu%2C+Yang&rft.date=2024-12-06&rft.issn=1556-5297&rft.eissn=1556-5300&rft.volume=21&rft.issue=4&rft.spage=605&rft_id=info:doi/10.62617%2Fmcb605&rft.externalDBID=n%2Fa&rft.externalDocID=10_62617_mcb605 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1556-5297&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1556-5297&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1556-5297&client=summon |