A Spatiotemporal Graph Transformer Network for real-time ball trajectory monitoring and prediction in dynamic sports environments
Ball trajectory prediction in sports is a crucial task for real-time applications such as performance analytics and coaching systems. Existing methods often struggle to simultaneously capture the spatial relationships between players and the ball while modeling long-term temporal dependencies. To ad...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-04-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824015242 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087653341724672 |
|---|---|
| author | Zujian Li Dan Yu |
| author_facet | Zujian Li Dan Yu |
| author_sort | Zujian Li |
| collection | DOAJ |
| description | Ball trajectory prediction in sports is a crucial task for real-time applications such as performance analytics and coaching systems. Existing methods often struggle to simultaneously capture the spatial relationships between players and the ball while modeling long-term temporal dependencies. To address these limitations, we propose the Spatiotemporal Graph Transformer Network (SGTN), which integrates a Spatiotemporal Graph Convolutional Network (ST-GCN) with a Transformer architecture. This combination allows for precise modeling of dynamic sports scenarios by effectively handling both spatial and temporal data. Experimental results on the SoccerNet-v2 dataset demonstrate that SGTN significantly outperforms recent models in terms of prediction accuracy, trajectory coverage, and robustness, while maintaining competitive inference times suitable for real-time applications. SGTN achieves a significant 25% reduction in prediction error compared to existing models. This improvement underscores its enhanced accuracy, robustness, and real-time feasibility, making it highly suitable for applications such as live sports analysis, performance monitoring, and decision-making. The model’s ability to generalize across multi-scenario environments further demonstrates its potential applicability to other fields beyond sports, including autonomous systems and robotics. Our future work aims to enhance memory efficiency and optimize multi-scenario inference speed to broaden the model’s deployment in edge computing environments. |
| format | Article |
| id | doaj-art-064260474a7d40f3a5045846d072dc80 |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-064260474a7d40f3a5045846d072dc802025-02-06T05:11:11ZengElsevierAlexandria Engineering Journal1110-01682025-04-01119246258A Spatiotemporal Graph Transformer Network for real-time ball trajectory monitoring and prediction in dynamic sports environmentsZujian Li0Dan Yu1School of Rehabilitation Medicine, Gannan Medical University, Ganzhou, 341000, China; Corresponding author.The College of Education and Liberal Arts, Adamson University, Manila, 1000, PhilippinesBall trajectory prediction in sports is a crucial task for real-time applications such as performance analytics and coaching systems. Existing methods often struggle to simultaneously capture the spatial relationships between players and the ball while modeling long-term temporal dependencies. To address these limitations, we propose the Spatiotemporal Graph Transformer Network (SGTN), which integrates a Spatiotemporal Graph Convolutional Network (ST-GCN) with a Transformer architecture. This combination allows for precise modeling of dynamic sports scenarios by effectively handling both spatial and temporal data. Experimental results on the SoccerNet-v2 dataset demonstrate that SGTN significantly outperforms recent models in terms of prediction accuracy, trajectory coverage, and robustness, while maintaining competitive inference times suitable for real-time applications. SGTN achieves a significant 25% reduction in prediction error compared to existing models. This improvement underscores its enhanced accuracy, robustness, and real-time feasibility, making it highly suitable for applications such as live sports analysis, performance monitoring, and decision-making. The model’s ability to generalize across multi-scenario environments further demonstrates its potential applicability to other fields beyond sports, including autonomous systems and robotics. Our future work aims to enhance memory efficiency and optimize multi-scenario inference speed to broaden the model’s deployment in edge computing environments.http://www.sciencedirect.com/science/article/pii/S1110016824015242Spatiotemporal Graph Transformer NetworkBall trajectory predictionSports analyticsReal-time performanceSpatiotemporal Graph Convolutional NetworkTransformer architecture |
| spellingShingle | Zujian Li Dan Yu A Spatiotemporal Graph Transformer Network for real-time ball trajectory monitoring and prediction in dynamic sports environments Alexandria Engineering Journal Spatiotemporal Graph Transformer Network Ball trajectory prediction Sports analytics Real-time performance Spatiotemporal Graph Convolutional Network Transformer architecture |
| title | A Spatiotemporal Graph Transformer Network for real-time ball trajectory monitoring and prediction in dynamic sports environments |
| title_full | A Spatiotemporal Graph Transformer Network for real-time ball trajectory monitoring and prediction in dynamic sports environments |
| title_fullStr | A Spatiotemporal Graph Transformer Network for real-time ball trajectory monitoring and prediction in dynamic sports environments |
| title_full_unstemmed | A Spatiotemporal Graph Transformer Network for real-time ball trajectory monitoring and prediction in dynamic sports environments |
| title_short | A Spatiotemporal Graph Transformer Network for real-time ball trajectory monitoring and prediction in dynamic sports environments |
| title_sort | spatiotemporal graph transformer network for real time ball trajectory monitoring and prediction in dynamic sports environments |
| topic | Spatiotemporal Graph Transformer Network Ball trajectory prediction Sports analytics Real-time performance Spatiotemporal Graph Convolutional Network Transformer architecture |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824015242 |
| work_keys_str_mv | AT zujianli aspatiotemporalgraphtransformernetworkforrealtimeballtrajectorymonitoringandpredictionindynamicsportsenvironments AT danyu aspatiotemporalgraphtransformernetworkforrealtimeballtrajectorymonitoringandpredictionindynamicsportsenvironments AT zujianli spatiotemporalgraphtransformernetworkforrealtimeballtrajectorymonitoringandpredictionindynamicsportsenvironments AT danyu spatiotemporalgraphtransformernetworkforrealtimeballtrajectorymonitoringandpredictionindynamicsportsenvironments |