Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insights
<p dir="ltr">We present a sequential fusion-based real-time soccer video analytics approach designed to comprehensively understand ball–player interactions. Our approach leverages the power of deep computer vision models, employing a CSPDarknet53 backbone for detection and a Graph Co...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1864513534593859584 |
|---|---|
| author | Fahad Majeed (22466596) |
| author2 | Maria Nazir (22466599) Kamilla Swart (18279016) Marco Agus (8032898) Jens Schneider (16885948) |
| author2_role | author author author author |
| author_facet | Fahad Majeed (22466596) Maria Nazir (22466599) Kamilla Swart (18279016) Marco Agus (8032898) Jens Schneider (16885948) |
| author_role | author |
| dc.creator.none.fl_str_mv | Fahad Majeed (22466596) Maria Nazir (22466599) Kamilla Swart (18279016) Marco Agus (8032898) Jens Schneider (16885948) |
| dc.date.none.fl_str_mv | 2025-07-01T00:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1038/s41598-025-05462-7 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/Real-time_analysis_of_soccer_ball_player_interactions_using_graph_convolutional_networks_for_enhanced_game_insights/30405508 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Information and computing sciences Artificial intelligence Computer vision and multimedia computation Machine learning Sequential fusion Soccer player detection Tracking Soccer video analytics Speed estimation Graph convolutional networks |
| dc.title.none.fl_str_mv | Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insights |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">We present a sequential fusion-based real-time soccer video analytics approach designed to comprehensively understand ball–player interactions. Our approach leverages the power of deep computer vision models, employing a CSPDarknet53 backbone for detection and a Graph Convolutional Network (GCN) for predictive analytics. The proposed approach intricately analyzes ball–player interactions by evaluating metrics such as inter-player distances, proximity to the ball, and hierarchical sorting based on shortest distances to the ball. We also track and estimate each player’s total distance and speed covered throughout the game. Our method performs exceptionally well on both uni- and multi-directional player movements, uncovering unique patterns in soccer videos. Extensive experimental evaluations demonstrate the effectiveness of our approach, achieving 91% object detection accuracy, 90% tracking and action recognition accuracy, and 92% speed analysis accuracy on benchmark datasets. Furthermore, our approach outperforms existing GCN techniques, achieving accuracies of 92% in graph connectivity, 89% in node classification, 87% in player tracking, and 88% in event recognition. Here, we show that our method provides a robust and accurate solution for real-time soccer video analytics, offering valuable insights into player performance and team strategies.</p><h2>Other Information</h2><p dir="ltr">Published in: Scientific Reports<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s41598-025-05462-7" target="_blank">https://dx.doi.org/10.1038/s41598-025-05462-7</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_28732e4e077e5f694bee9ff3d9888f47 |
| identifier_str_mv | 10.1038/s41598-025-05462-7 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/30405508 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insightsFahad Majeed (22466596)Maria Nazir (22466599)Kamilla Swart (18279016)Marco Agus (8032898)Jens Schneider (16885948)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationMachine learningSequential fusionSoccer player detectionTrackingSoccer video analyticsSpeed estimationGraph convolutional networks<p dir="ltr">We present a sequential fusion-based real-time soccer video analytics approach designed to comprehensively understand ball–player interactions. Our approach leverages the power of deep computer vision models, employing a CSPDarknet53 backbone for detection and a Graph Convolutional Network (GCN) for predictive analytics. The proposed approach intricately analyzes ball–player interactions by evaluating metrics such as inter-player distances, proximity to the ball, and hierarchical sorting based on shortest distances to the ball. We also track and estimate each player’s total distance and speed covered throughout the game. Our method performs exceptionally well on both uni- and multi-directional player movements, uncovering unique patterns in soccer videos. Extensive experimental evaluations demonstrate the effectiveness of our approach, achieving 91% object detection accuracy, 90% tracking and action recognition accuracy, and 92% speed analysis accuracy on benchmark datasets. Furthermore, our approach outperforms existing GCN techniques, achieving accuracies of 92% in graph connectivity, 89% in node classification, 87% in player tracking, and 88% in event recognition. Here, we show that our method provides a robust and accurate solution for real-time soccer video analytics, offering valuable insights into player performance and team strategies.</p><h2>Other Information</h2><p dir="ltr">Published in: Scientific Reports<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s41598-025-05462-7" target="_blank">https://dx.doi.org/10.1038/s41598-025-05462-7</a></p>2025-07-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1038/s41598-025-05462-7https://figshare.com/articles/journal_contribution/Real-time_analysis_of_soccer_ball_player_interactions_using_graph_convolutional_networks_for_enhanced_game_insights/30405508CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/304055082025-07-01T00:00:00Z |
| spellingShingle | Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insights Fahad Majeed (22466596) Information and computing sciences Artificial intelligence Computer vision and multimedia computation Machine learning Sequential fusion Soccer player detection Tracking Soccer video analytics Speed estimation Graph convolutional networks |
| status_str | publishedVersion |
| title | Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insights |
| title_full | Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insights |
| title_fullStr | Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insights |
| title_full_unstemmed | Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insights |
| title_short | Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insights |
| title_sort | Real-time analysis of soccer ball–player interactions using graph convolutional networks for enhanced game insights |
| topic | Information and computing sciences Artificial intelligence Computer vision and multimedia computation Machine learning Sequential fusion Soccer player detection Tracking Soccer video analytics Speed estimation Graph convolutional networks |