An Algorithm for Extracting Features of Basketball Players' Foul Actions Based on an Attention Mechanism

Basketball foul action usually involves multiple features, and it is difficult to extract effective features from complex and diverse features. Therefore, a feature extraction algorithm for basketball players' foul action based on attention mechanism is proposed. On the basis of ResNet50 networ...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of computational intelligence systems Vol. 18; no. 1; pp. 1 - 15
Main Author Wang, Peng
Format Journal Article
LanguageEnglish
Published Dordrecht Springer Netherlands 24.02.2025
Springer Nature B.V
Springer
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Basketball foul action usually involves multiple features, and it is difficult to extract effective features from complex and diverse features. Therefore, a feature extraction algorithm for basketball players' foul action based on attention mechanism is proposed. On the basis of ResNet50 network model, the attention mechanism is integrated to build a basketball player foul action feature extraction model. The machine vision system is used to obtain basketball player action video as the input of the model. The space attention module and time attention module are, respectively, introduced into the video slow frame rate branch and video fast frame rate branch of ResNet50 network. By making the network give greater weight to the key areas of a single frame of video, and improving the network's attention to important video frames, the best spatio-temporal characteristics of foul actions are obtained. After fusion, the feature fusion results are input into the classifier with the cross-entropy loss function as the loss function, and the probability value of each possible foul action and the tag target probability are output, complete basketball player foul action feature extraction. The experimental results show that the algorithm can effectively identify the identification of basketball players, the cumulative matching feature value of foul action recognition can reach more than 95%, and the average accuracy is more than 70%; the F 1 value and stability are high, which can reduce the error caused by data fluctuation and noise; the error rate of real-time detection is less than 4.5%, the omission rate is less than 4.7%, the detection time is lower than 14 ms, and the application effect is good.
AbstractList Basketball foul action usually involves multiple features, and it is difficult to extract effective features from complex and diverse features. Therefore, a feature extraction algorithm for basketball players' foul action based on attention mechanism is proposed. On the basis of ResNet50 network model, the attention mechanism is integrated to build a basketball player foul action feature extraction model. The machine vision system is used to obtain basketball player action video as the input of the model. The space attention module and time attention module are, respectively, introduced into the video slow frame rate branch and video fast frame rate branch of ResNet50 network. By making the network give greater weight to the key areas of a single frame of video, and improving the network's attention to important video frames, the best spatio-temporal characteristics of foul actions are obtained. After fusion, the feature fusion results are input into the classifier with the cross-entropy loss function as the loss function, and the probability value of each possible foul action and the tag target probability are output, complete basketball player foul action feature extraction. The experimental results show that the algorithm can effectively identify the identification of basketball players, the cumulative matching feature value of foul action recognition can reach more than 95%, and the average accuracy is more than 70%; the F1 value and stability are high, which can reduce the error caused by data fluctuation and noise; the error rate of real-time detection is less than 4.5%, the omission rate is less than 4.7%, the detection time is lower than 14 ms, and the application effect is good.
Abstract Basketball foul action usually involves multiple features, and it is difficult to extract effective features from complex and diverse features. Therefore, a feature extraction algorithm for basketball players' foul action based on attention mechanism is proposed. On the basis of ResNet50 network model, the attention mechanism is integrated to build a basketball player foul action feature extraction model. The machine vision system is used to obtain basketball player action video as the input of the model. The space attention module and time attention module are, respectively, introduced into the video slow frame rate branch and video fast frame rate branch of ResNet50 network. By making the network give greater weight to the key areas of a single frame of video, and improving the network's attention to important video frames, the best spatio-temporal characteristics of foul actions are obtained. After fusion, the feature fusion results are input into the classifier with the cross-entropy loss function as the loss function, and the probability value of each possible foul action and the tag target probability are output, complete basketball player foul action feature extraction. The experimental results show that the algorithm can effectively identify the identification of basketball players, the cumulative matching feature value of foul action recognition can reach more than 95%, and the average accuracy is more than 70%; the F1 value and stability are high, which can reduce the error caused by data fluctuation and noise; the error rate of real-time detection is less than 4.5%, the omission rate is less than 4.7%, the detection time is lower than 14 ms, and the application effect is good.
Basketball foul action usually involves multiple features, and it is difficult to extract effective features from complex and diverse features. Therefore, a feature extraction algorithm for basketball players' foul action based on attention mechanism is proposed. On the basis of ResNet50 network model, the attention mechanism is integrated to build a basketball player foul action feature extraction model. The machine vision system is used to obtain basketball player action video as the input of the model. The space attention module and time attention module are, respectively, introduced into the video slow frame rate branch and video fast frame rate branch of ResNet50 network. By making the network give greater weight to the key areas of a single frame of video, and improving the network's attention to important video frames, the best spatio-temporal characteristics of foul actions are obtained. After fusion, the feature fusion results are input into the classifier with the cross-entropy loss function as the loss function, and the probability value of each possible foul action and the tag target probability are output, complete basketball player foul action feature extraction. The experimental results show that the algorithm can effectively identify the identification of basketball players, the cumulative matching feature value of foul action recognition can reach more than 95%, and the average accuracy is more than 70%; the F 1 value and stability are high, which can reduce the error caused by data fluctuation and noise; the error rate of real-time detection is less than 4.5%, the omission rate is less than 4.7%, the detection time is lower than 14 ms, and the application effect is good.
ArticleNumber 40
Author Wang, Peng
Author_xml – sequence: 1
  givenname: Peng
  surname: Wang
  fullname: Wang, Peng
  email: wangpeng01268@163.com
  organization: Physical Education Institute, Henan Kaifeng College of Science Technology and Communication
BookMark eNp9kU9vFCEYh4lpE2vtF_BE4sHTWP7PcFybrm1So4d6Ji8D7M46CxXYpP32sp3GevIEvHl-D2_ye4dOYooeoQ-UfKaE9JdFCKpVR5js2lPwTr5BZ3ToZaeGgZ_8c3-LLkrZEUIYFYQIcYa2q4hX8yblqW73OKSMrx9rhrFOcYPXHuoh-4JTwF-g_PLVwjzjHzM8-Vw-4XU6zHjV2BTLEfAOp4ihGWv18TjG3_y4hTiV_Xt0GmAu_uLlPEc_19f3Vzfd3fevt1eru27klNRO2IH0QQkJlAzWUR2c9r3rGSgdBsm4Fk4DWE0CMCetGqinig3WOzdyAfwc3S5el2BnHvK0h_xkEkzmeZDyxkCu0zh7E0bGiQBrnZdCSwlWhSCcZK7XrG3TXB8X10NOvw--VLNLhxzb-obTnmiipFSNYgs15lRK9uHvr5SYY0FmKci0gsxzQUa2EF9CpcFx4_Or-j-pPxc-lI4
Cites_doi 10.1142/S0129065723500193
10.1049/iet-ipr.2019.0230
10.1108/SBM-10-2021-0119
10.1519/JSC.0000000000002876
10.1007/s40279-021-01584-w
10.1111/exsy.12555
ContentType Journal Article
Copyright The Author(s) 2025
Copyright Springer Nature B.V. 2025
Copyright_xml – notice: The Author(s) 2025
– notice: Copyright Springer Nature B.V. 2025
DBID C6C
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOA
DOI 10.1007/s44196-025-00743-5
DatabaseName Springer Nature OA Free Journals
CrossRef
Computer and Information Systems 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
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts


Database_xml – sequence: 1
  dbid: C6C
  name: Springer Nature OA Free Journals
  url: http://www.springeropen.com/
  sourceTypes: Publisher
– sequence: 2
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1875-6883
EndPage 15
ExternalDocumentID oai_doaj_org_article_fc2304abbde54955ab6ff4d52d792310
10_1007_s44196_025_00743_5
GroupedDBID 0R~
4.4
5GY
AAFWJ
AAJSJ
AAKKN
AAYZJ
ABEEZ
ABFIM
ACACY
ACGFS
ACULB
ADBBV
ADCVX
AENEX
AFGXO
AFKRA
AFPKN
ALMA_UNASSIGNED_HOLDINGS
ARAPS
ARCSS
AVBZW
BCNDV
BENPR
BGLVJ
C24
C6C
CS3
DU5
EBLON
EBS
EJD
GROUPED_DOAJ
GTTXZ
HCIFZ
HZ~
J~4
K7-
O9-
OK1
PIMPY
RSV
SOJ
TFW
TR2
AASML
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c310t-4b807f645a108bd19fd9e7d72a69f852394d9aab90fa2d5b681e1628beddc34a3
IEDL.DBID DOA
ISSN 1875-6883
1875-6891
IngestDate Wed Aug 27 01:31:46 EDT 2025
Thu Jul 24 01:44:55 EDT 2025
Tue Jul 01 05:40:37 EDT 2025
Tue Feb 25 01:11:52 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Machine vision system
Temporal attention
Feature extraction
Foul action
Spatial attention
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c310t-4b807f645a108bd19fd9e7d72a69f852394d9aab90fa2d5b681e1628beddc34a3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://doaj.org/article/fc2304abbde54955ab6ff4d52d792310
PQID 3170906556
PQPubID 4869256
PageCount 15
ParticipantIDs doaj_primary_oai_doaj_org_article_fc2304abbde54955ab6ff4d52d792310
proquest_journals_3170906556
crossref_primary_10_1007_s44196_025_00743_5
springer_journals_10_1007_s44196_025_00743_5
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2025-02-24
PublicationDateYYYYMMDD 2025-02-24
PublicationDate_xml – month: 02
  year: 2025
  text: 2025-02-24
  day: 24
PublicationDecade 2020
PublicationPlace Dordrecht
PublicationPlace_xml – name: Dordrecht
– name: Abingdon
PublicationTitle International journal of computational intelligence systems
PublicationTitleAbbrev Int J Comput Intell Syst
PublicationYear 2025
Publisher Springer Netherlands
Springer Nature B.V
Springer
Publisher_xml – name: Springer Netherlands
– name: Springer Nature B.V
– name: Springer
References VJ Hase (743_CR8) 2020; 7
P Sharma (743_CR5) 2020; 14
P Ushapreethi (743_CR16) 2021; 6
WQ Zhan (743_CR13) 2020; 41
WP Luo (743_CR10) 2021; 49
A Sachan (743_CR7) 2021; 225
K Christos (743_CR3) 2020; 20
M Rogers (743_CR1) 2022; 52
GJ Sanders (743_CR2) 2021; 35
CH Wang (743_CR12) 2023; 40
S Kilicarslan (743_CR14) 2021; 174
S Panda (743_CR15) 2020; 37
D Siemon (743_CR11) 2023; 13
López-Laval (743_CR4) 2021; 30
AR Colligan (743_CR6) 2022; 147
JE Arco (743_CR9) 2023; 33
References_xml – volume: 20
  start-page: 3651
  issue: 6
  year: 2020
  ident: 743_CR3
  publication-title: J. Phys. Educ. Sport
– volume: 225
  start-page: 108785.1
  issue: 4
  year: 2021
  ident: 743_CR7
  publication-title: Ocean Eng.
– volume: 33
  start-page: 2350019
  issue: 4
  year: 2023
  ident: 743_CR9
  publication-title: Int. J. Neural Syst.
  doi: 10.1142/S0129065723500193
– volume: 49
  start-page: 71
  issue: 2
  year: 2021
  ident: 743_CR10
  publication-title: Wool Text. J.
– volume: 174
  start-page: 114805.1
  issue: 7
  year: 2021
  ident: 743_CR14
  publication-title: Expert Syst. Appl.
– volume: 7
  start-page: 267
  issue: 1/2/3
  year: 2020
  ident: 743_CR8
  publication-title: Int. J. Intell. Enterp.
– volume: 6
  start-page: 40
  issue: 1
  year: 2021
  ident: 743_CR16
  publication-title: Int. J. Veh. Inf. Commun. Syst.
– volume: 14
  start-page: 909
  issue: 5
  year: 2020
  ident: 743_CR5
  publication-title: IET Image Proc.
  doi: 10.1049/iet-ipr.2019.0230
– volume: 13
  start-page: 228
  issue: 2
  year: 2023
  ident: 743_CR11
  publication-title: Sport Bus. Manag. Int. J.
  doi: 10.1108/SBM-10-2021-0119
– volume: 35
  start-page: 1095
  issue: 4
  year: 2021
  ident: 743_CR2
  publication-title: J. Strength Condit. Res.
  doi: 10.1519/JSC.0000000000002876
– volume: 40
  start-page: 170
  issue: 11
  year: 2023
  ident: 743_CR12
  publication-title: Comput. Simul.
– volume: 30
  start-page: 240
  issue: 2
  year: 2021
  ident: 743_CR4
  publication-title: Revista de Psicologia del Deporte
– volume: 52
  start-page: 1175
  issue: 5
  year: 2022
  ident: 743_CR1
  publication-title: Sports Med.
  doi: 10.1007/s40279-021-01584-w
– volume: 147
  start-page: 103226.1
  issue: 17
  year: 2022
  ident: 743_CR6
  publication-title: Comput.-Aided Des.
– volume: 41
  start-page: 268
  issue: 3
  year: 2020
  ident: 743_CR13
  publication-title: J. Jiangsu Univ. (Natural Science Edition)
– volume: 37
  start-page: 12555.1
  issue: 5
  year: 2020
  ident: 743_CR15
  publication-title: Expert. Syst.
  doi: 10.1111/exsy.12555
SSID ssj0002140044
ssib050732782
Score 2.3424509
Snippet Basketball foul action usually involves multiple features, and it is difficult to extract effective features from complex and diverse features. Therefore, a...
Abstract Basketball foul action usually involves multiple features, and it is difficult to extract effective features from complex and diverse features....
SourceID doaj
proquest
crossref
springer
SourceType Open Website
Aggregation Database
Index Database
Publisher
StartPage 1
SubjectTerms Algorithms
Artificial Intelligence
Basketball
Computational Intelligence
Control
Engineering
Entropy (Information theory)
Error detection
Feature extraction
Foul action
Machine vision
Machine vision system
Mathematical Logic and Foundations
Mechatronics
Modules
Players
Real time
Research Article
Robotics
Spatial attention
Temporal attention
Vision systems
SummonAdditionalLinks – databaseName: Springer Nature OA Free Journals
  dbid: C6C
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB0VeoEDbaEV29LKh0ocwGri2E58XFasVpW26gEkbpadsQF1SRDJSvz82t7stiB66DVxPuQ3o3lje94AfJXKVkyhpTlmjvLClFQhQ-o5FrYuM8OT8Pz8h5xd8u9X4mqQyYm1MM_27791IVynY7KCpmhHxRa8FnlRxjYNEznZrKewPFojH-piXn70SexJEv1PeOWzrdAUYaZvYW-ghmS8wvIdvHLNPrxZt10ggxfuw-5fGoIHcDNuyHhx3YYk_-aOBApKzh_7VPrUXJNI8JYhoSatJ2em--V6axYL8nNhItM-JtN2GT6YShu6OMAhaRtiwhv7fnUOksxdrA2-7e7ew-X0_GIyo0P7BFoHztZTbqus9JILk2eVxVx5VK7EkhmpfCViT3RUxliVecNQWFnlLpessg6xLrgpPsB20zbuEIgrSlSWYVZzx2M4w8ojlyZkI85VtRnByXpi9f1KJUNv9JATDDrAoBMMWozgLM79ZmRUuE4XAvB6cBjt67hcbaxFF1JYIYyVPhiQYFgmTjqCozVyenC7TgcylKlAqoQcwekazT-3__1LH_9v-CfYYcmuGGX8CLb7h6X7HMhJb78kq_wNTl3bqw
  priority: 102
  providerName: Springer Nature
Title An Algorithm for Extracting Features of Basketball Players' Foul Actions Based on an Attention Mechanism
URI https://link.springer.com/article/10.1007/s44196-025-00743-5
https://www.proquest.com/docview/3170906556
https://doaj.org/article/fc2304abbde54955ab6ff4d52d792310
Volume 18
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA7qyYtvcX2Rg-BBg22apM1xXVwWYcWDgreQdBIV11bcLvjzTdKuLxAvXnpoQxq-mWS-aeeB0JGQpqASDEkhsYRlOicSKBDHIDNlnmgWC8-Pr8Toll3e8bsvrb5CTFhbHrgF7syV4bOlNgasd2U410Y4PxGnkEduEk5fb_O-OFPhDKZp0E3WZcnEXDlv92O8LSfRbBL-zRLFgv3fWOaPH6PR3gzX0EpHFHG_XeA6WrDVBlqdN2HA3Z7cRA_9Cvcn97V38h-esaeg-OKtialP1T0OBG_mHWpcO3yup0-2MXoywdcTHZj2MR7WM_-KmNowDQMs4LrC2s_YNG0cJB7bkBv8OH3eQrfDi5vBiHTtE0jpcWkIM0WSO8G4TpPCQCodSJtDTrWQruChJzpIrY1MnKbAjShSmwpaGAtQZkxn22ipqiu7g7DNcpCGQlIyy4I5g8IBE9p7I9YWpe6hkzmU6qWtkqE-6iFH4JUHXkXgFe-h84D2x8hQ4Tre8HJXndzVX3Lvof25rFS37abKk6FEelLFRQ-dzuX3-fj3Je3-x5L20DKN-kUJZftoqXmd2QNPWRpziBYHlIWrGBxGTX0HDdvo4A
linkProvider Directory of Open Access Journals
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Nb9QwEB2VcgAOfBQqFkrxAcQBLCWOncQHDtvS1ZZ2Kw6t1JuxM862YpugTVbA_-kPre1NlhbBgUOvieVYnhnPm3jeDMCbVJqcSTQ0xshSnuiMSmRIS46JKbJI81B4fnKUjk_451NxugaXPRcmZLv3V5LhpF6R3ZzjDgmzgga_R_tUygP764cL1JqP-5-cVN8yNto73h3TrpcALRyAaSk3eZSVKRc6jnKDsSxR2gwzplNZ5sI3CEeptZFRqRkKk-axjVOWG4tYJFwnbt47cNctIfeJg7sdp8Kf9yz2dsA7Rs7fl3rD64XmADcQ7R-XsMG3jR7Dww6UkuFSi57Amq024FHf8IF09r8BD65VL3wKZ8OKDGfTen7enl0QB37J3s82kK6qKfHQcuFCeVKXZEc332xr9GxGvsy0x_jvyKheuA8GUkXjB1gkdUW0m7FtlxmYZGI9K_m8uXgGJ7ey2ZuwXtWVfQ7EJhlKwzAquOXekWJeIk-1i4OszQs9gPf9xqrvy_ocalWJOYhBOTGoIAYlBrDj93410tfWDg_q-VR1pqrKwv8o18agdcGzENqkpVNdwTALaHgAW73kVGfwjXIwLJIOzol0AB96af5-_e8lvfi_4a_h3vh4cqgO948OXsJ9FnSMUca3YL2dL-wrB5Fasx00lMDX2zaJK9mPHTY
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Nb9QwEB2VIiE48FFALBTwAcQBoiaO7cQHDtttVy2lVQ9U6s3YGXtbsU2q3ayAf8VPxPYmC0Vw4NBrYjmWZybzxp43A_BKSFNSiSbJMLUJy3WRSKSYOIa5qYpUs1h4_vBI7J2wD6f8dA1-9FyYmO3eX0kuOQ2hSlPdbl2i21oR37wTj8mzPIk-MOnTKg_s968-aJu_39_xEn5N6Xj302gv6foKJJUHM23CTJkWTjCus7Q0mEmH0hZYUC2kK3loFo5SayNTpylyI8rMZoKWxiJWOdO5n_cG3PSRURbCvZEYrU51aBZsgnXsnL8v9YoHjI0CrqDbPy5ko58b34e7HUAlw6VGPYA1W2_Avb75A-n-BRtw57dKhg_hbFiT4XTSzM7bswvigTDZ_dZGAlY9IQFmLnxYTxpHtvX8i22Nnk7J8VQHvP-GjJuF_2AkWMzDAIukqYn2M7btMhuTHNrAUD6fXzyCk2vZ7MewXje1fQLE5gVKQzGtmGXBqWLpkAntYyJry0oP4G2_sepyWatDraoyRzEoLwYVxaD4ALbD3q9Ghjrb8UEzm6jObJWrwqG5NgatD6Q510Y4r8acYhGR8QA2e8mpzvjnykOyVHpox8UA3vXS_PX630t6-n_DX8Kt452x-rh_dPAMbtOoYjShbBPW29nCPvdoqTUvooIS-HzdFvETv7YhmQ
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=An+Algorithm+for+Extracting+Features+of+Basketball+Players%27+Foul+Actions+Based+on+an+Attention+Mechanism&rft.jtitle=International+journal+of+computational+intelligence+systems&rft.date=2025-02-24&rft.pub=Springer+Nature+B.V&rft.issn=1875-6891&rft.eissn=1875-6883&rft.volume=18&rft.issue=1&rft_id=info:doi/10.1007%2Fs44196-025-00743-5&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1875-6883&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1875-6883&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1875-6883&client=summon