Exercise and Sport Science, Faculty of Medicine and Health, The University of Sydney, Sydney, Australia.
School of Life Science and Education, Staffordshire University, Stoke on Trent, UK.
J Sports Sci. 2021 Mar;39(5):513-522. doi: 10.1080/02640414.2020.1832735. Epub 2020 Oct 14.
Video analysis is used in sport to derive kinematic variables of interest but often relies on time-consuming tracking operations. The purpose of this study was to determine speed, accuracy and reliability of 2D body landmark digitisation by a neural network (NN), compared with manual digitisation, for the glide phase in swimming. Glide variables including glide factor; instantaneous hip angles, trunk inclines and horizontal velocities were selected as they influence performance and are susceptible to digitisation propagation error. The NN was "trained" on 400 frames of 2D glide video from a sample of eight elite swimmers. Four glide trials of another swimmer were used to test agreement between the NN and a manual operator for body marker position data of the knee, hip and shoulder, and the effect of digitisation on glide variables. The NN digitised body landmarks 233 times faster than the manual operator, with digitising root-mean-square-error of ~4-5 mm. High accuracy and reliability was found between body position and glide variable data between the two methods with relative error ≤5.4% and correlation coefficients >0.95 for all variables. NNs could be applied to greatly reduce the time of kinematic analysis in sports and facilitate rapid feedback of performance measures.
视频分析被用于运动领域，以获取运动学变量，但通常依赖于耗时的跟踪操作。本研究的目的是确定神经网络（NN）与手动数字化相比，在游泳滑行阶段对 2D 身体标志点进行数字化的速度、准确性和可靠性。选择滑行变量，包括滑行因子、即时髋角、躯干倾斜度和水平速度，因为它们影响性能，并且容易受到数字化传播误差的影响。NN 是在 8 名优秀游泳运动员的样本中 400 帧 2D 滑行视频上“训练”的。另一名游泳运动员的 4 次滑行试验用于测试 NN 与手动操作员之间的一致性，用于膝关节、髋关节和肩部的身体标记位置数据，以及数字化对滑行变量的影响。NN 对身体标志点的数字化速度比手动操作员快 233 倍，数字化均方根误差约为 4-5 毫米。两种方法之间的身体位置和滑行变量数据具有很高的准确性和可靠性，所有变量的相对误差均≤5.4%，相关系数均>0.95。NN 可应用于大大减少运动中运动学分析的时间，并促进快速反馈性能测量。
