SoccerTrack v2: A Full-Pitch Multi-View Soccer Dataset for Game State Reconstruction

TL;DR

SoccerTrack v2 introduces a comprehensive, high-resolution soccer dataset with full-pitch multi-view recordings, detailed annotations, and labels for game state and actions, aiming to enhance research in soccer analytics and computer vision.

Contribution

The paper presents SoccerTrack v2, a novel large-scale, fully annotated soccer dataset with panoramic 4K videos, enabling advanced research in game state reconstruction and action spotting.

Findings

Provides 10 full-length panoramic 4K soccer videos with detailed annotations.

Enables new benchmarks for multi-object tracking and game state reconstruction.

Facilitates development of automated tactical analysis tools.

Abstract

SoccerTrack v2 is a new public dataset for advancing multi-object tracking (MOT), game state reconstruction (GSR), and ball action spotting (BAS) in soccer analytics. Unlike prior datasets that use broadcast views or limited scenarios, SoccerTrack v2 provides 10 full-length, panoramic 4K recordings of university-level matches, captured with BePro cameras for complete player visibility. Each video is annotated with GSR labels (2D pitch coordinates, jersey-based player IDs, roles, teams) and BAS labels for 12 action classes (e.g., Pass, Drive, Shot). This technical report outlines the datasets structure, collection pipeline, and annotation process. SoccerTrack v2 is designed to advance research in computer vision and soccer analytics, enabling new benchmarks and practical applications in tactical analysis and automated tools.