基于深扩展IoU与全局轨迹关联，提升鱼眼镜头下足球追踪精度。
GTATrack: Winner Solution to SoccerTrack 2025 with Deep-EIoU and Global Tracklet Association
- 分两阶段设计：先用深扩展IoU实现无运动假设的在线匹配，再通过全局轨迹优化
- 在SoccerTrack 2025中取得0.60的HOTA得分，误报仅982个，显著减少身份混淆
- 适合需要高精度体育视频追踪的场景，尤其适用于广角畸变镜头
体育场景中的多目标追踪因球员运动不规则、外观相似及频繁遮挡而极具挑战性，静态鱼眼相机引入的几何畸变与极端尺度变化进一步加剧难题。本文提出GTATrack，一种分层追踪框架，在SoccerTrack Challenge 2025中获第一名。该框架集成两项核心组件：用于无运动假设在线关联的深度扩展交并比（Deep-EIoU）和用于轨迹级优化的全局轨迹关联（GTA）。这种两阶段设计兼顾短期匹配鲁棒性与长期身份一致性。此外，采用伪标签策略提升小目标与畸变目标的检测召回率。局部关联与全局推理的协同有效缓解了身份切换、遮挡与追踪碎片化问题。方法在测试集上实现0.60的领先HOTA分数，误报数仅为982，验证了其在鱼眼摄像头下的先进性能。代码已公开于https://github.com/ron941/GTATrack-STC2025。
原文摘要 · Abstract (English)
Multi-object tracking (MOT) in sports is highly challenging due to irregular player motion, uniform appearances, and frequent occlusions. These difficulties are further exacerbated by the geometric distortion and extreme scale variation introduced by static fisheye cameras. In this work, we present GTATrack, a hierarchical tracking framework that win first place in the SoccerTrack Challenge 2025. GTATrack integrates two core components: Deep Expansion IoU (Deep-EIoU) for motion-agnostic online association and Global Tracklet Association (GTA) for trajectory-level refinement. This two-stage design enables both robust short-term matching and long-term identity consistency. Additionally, a pseudo-labeling strategy is used to boost detector recall on small and distorted targets. The synergy between local association and global reasoning effectively addresses identity switches, occlusions, and tracking fragmentation. Our method achieved a winning HOTA score of 0.60 and significantly reduced false positives to 982, demonstrating state-of-the-art accuracy in fisheye-based soccer tracking. Our code is available at https://github.com/ron941/GTATrack-STC2025.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。