用于体育视频分析的无训练长期多目标跟踪
Training-Free Long-Term Multi-Object Tracking for Sports Video Analytics
- Inria（法国国家信息与自动化研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对体育视频长期多目标跟踪的挑战，提出无训练的McByte++框架，通过整合轻量掩码传播等技术提升效率与性能，在相关基准测试中取得显著指标提升且速度大幅加快。
AI中文摘要：
体育领域的长期多目标跟踪仍存在诸多挑战，如频繁遮挡、相机快速运动以及运动员重复出现等问题。本文提出McByte++，这是一种无训练的检测跟踪框架，在统一流程中整合了轻量级掩码传播、条件相机运动补偿和在线重识别。与其前身相比，McByte++大幅提升了运行效率，同时增强了身份保留能力。在SoccerNet-tracking和SportsMOT基准测试中，McByte++在线设置下相比原始McByte实现了最高+3.0的HOTA和+6.1的IDF1提升，结合离线全局关联时还能进一步提升性能。替换重型分割组件并优化运动建模，可实现最高一个数量级的速度提升。所有结果均在无需重新训练检测器或针对特定数据集调优的情况下获得，代码将在该https URL处提供。
英文摘要：
Long-term multi-object tracking in sports remains challenging due to frequent occlusions, rapid camera motion, and repeated player reappearances. We introduce McByte++, a training-free tracking-by-detection framework that integrates lightweight mask propagation, conditional camera motion compensation, and online re-identification within a unified pipeline. Compared to its predecessor, McByte++ substantially improves runtime efficiency while enhancing identity preservation. On SoccerNet-tracking and SportsMOT benchmarks, McByte++ achieves up to +3.0 HOTA and +6.1 IDF1 improvements over the original McByte in the online setting, with further gains when combined with offline global association. Replacing heavy segmentation components and optimizing motion modeling yields up to an order-of-magnitude speed increase. All results are obtained without detector retraining or dataset-specific tuning. Code will be made available at https://github.com/tstanczyk95/McBytePlusPlus.
