arXiv 2602.229412026-02cs.CV

基于平移和缩放视频记录的皮划艇冲刺团队船只速度和划桨率重建

Velocity and stroke rate reconstruction of canoe sprint team boats based on panned and zoomed video recordings

Laboratory for Biosignal Processing, Leipzig University of Applied Sciences, Leipzig, Germany（生物信号处理实验室，莱比锡应用科学大学，莱比锡，德国）；Research Group Canoeing, Institute for Applied Training Science (IAT), Leipzig, Germany（划船研究组，应用训练科学研究所（IAT），莱比锡，德国）；German Canoe Federation, Duisburg, Germany（德国皮划艇联合会，杜伊斯堡，德国）

Julian Ziegler, Daniel Matthes, Finn Gerdts, Patrick Frenzel, Torsten Warnke, Matthias Englert, Tina Koevari, Mirco Fuchs

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出了一种基于平移和缩放视频记录重建皮划艇冲刺团队船只速度和划桨率的方法，利用YOLOv8检测浮标和运动员，结合已知的浮标网格估计同源性，通过U-Net进行船体校准以估计船的位置，并利用光流实现鲁棒跟踪，最终提取划桨率信息，实验结果表明其速度和划桨率的MAPE分别达到0.011和0.009，具有高精度和自动化反馈。

摘要：

节奏策略，由速度和划桨率曲线定义，对于皮划艇冲刺的峰值表现至关重要。尽管GPS是分析的黄金标准，但其有限的可用性需要自动化视频分析方法。本文提出了一种扩展框架，用于从平移和缩放的视频记录中重建所有冲刺项目（K1-K4，C1-C2）和距离（200m-500m）的性能指标。我们的方法利用YOLOv8进行浮标和运动员检测，利用已知的浮标网格估计同源性。我们通过学习特定船体的运动员偏移量来一般化估计船的位置，利用U-Net进行船体校准。进一步，我们通过光流实现鲁棒的跟踪方案以适应多运动员船体类型。最后，我们介绍了从姿态估计或运动员边界框本身提取划桨率信息的方法。与精英比赛GPS数据的评估显示，速度的MAPE为0.011 [0.008 0.014]（Spearman rho=0.974）和划桨率的MAPE为0.009 [0.006 0.013]（Spearman rho=0.975）。这些方法为教练提供了高精度、自动化的反馈，且无需传感器，仅需极少的手动初始化工作。

英文摘要：

Pacing strategies, defined by velocity and stroke rate profiles, are essential for peak performance in canoe sprint. While GPS is the gold standard for analysis, its limited availability necessitates automated video-based solutions. This paper presents an extended framework for reconstructing performance metrics from panned and zoomed video recordings across all sprint disciplines (K1-K4, C1-C2) and distances (200m-500m). Our method utilizes YOLOv8 for buoy and athlete detection, leveraging the known buoy grid to estimate homographies. We generalized the estimation of the boat position by means of learning a boat-specific athlete offset using a U-net based boat tip calibration. Further, we implement a robust tracking scheme using optical flow to adapt to multi-athlete boat types. Finally, we introduce methods to extract stroke rate information from either pose estimations or the athlete bounding boxes themselves. Evaluation against GPS data from elite competitions yields a velocity MAPE of 0.011 [0.008 0.014] (Spearman rho=0.974) and a stroke rate MAPE of 0.009 [0.006 0.013] (Spearman rho = 0.975). The methods provide coaches with highly accurate, automated feedback with minimal manual initialization work required, and without requiring sensors.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。