https://github.com/SoccerNet/sn-gamestate

[CVPRW'24] SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap (CVPR24 - CVSports workshop)
https://github.com/SoccerNet/sn-gamestate

bird-eye-view detection multi-object-tracking re-identification soccer soccernet sports sports-analytics tracking video-understanding

Last synced: about 1 month ago
JSON representation

[CVPRW'24] SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap (CVPR24 - CVSports workshop)

• Host: GitHub
• URL: https://github.com/SoccerNet/sn-gamestate
• Owner: SoccerNet
• License: gpl-3.0
• Created: 2024-02-05T08:32:46.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-02-09T12:00:49.000Z (3 months ago)
• Last Synced: 2025-02-09T13:19:08.009Z (3 months ago)
• Topics: bird-eye-view, detection, multi-object-tracking, re-identification, soccer, soccernet, sports, sports-analytics, tracking, video-understanding
• Language: Python
• Homepage:
• Size: 95.9 MB
• Stars: 270
• Watchers: 19
• Forks: 55
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-cvpr-2024 - SoccerNet Game State Reconstruction - gamestate?style=social)](https://github.com/SoccerNet/sn-gamestate) [](https://arxiv.org/abs/2404.11335) | SoccerNet Game State Reconstruction (GSR) is a novel computer vision task involving the tracking and identification of sports players from a single moving camera to construct a video game-like minimap, without any specific hardware worn by the players. SoccerNet-GSR, the released dataset, includes 200 clips with 9.37M pitch localization annotations and 2.36M athlete positions on the pitch with their role, team & jersey number. Furthermore, a new performance metric 'GS-HOTA' is introduced to evaluate GSR methods. | (📊 Datasets/Benchmarks)