Action detection of volleyball using features based on clustering of body trajectories
Action detection of volleyball using features based on clustering of body trajectories
复制标题
基于身体轨迹聚类的特征进行排球动作检测
DOI：
10.11371/iieej.45.373
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
T. Ikenaga
中科院分区：
文献类型：
--
作者：
Eijiro Kubota;Takahiro Suzuki;M. Honda;T. Ikenaga
为了创造排球等运动的新战术，对运动员在真实的比赛中的动作进行分析变得越来越重要。然而，由于目前分析所需的运动数据是通过人类观察捕获的，因此高度期望来自摄像机的自动捕获系统能够容易地收集许多有用的数据。提出了一种基于运动特征的排球运动员动作检测算法。由于手臂和腿的身体轨迹是相似的，聚类利用它们的轨迹的形状、位置和密度。此外，聚类的特征值通过它们的均值和方差进行聚合。实验结果表明，基于该算法的运动检测系统对高清摄像机拍摄的排球比赛视频中的拦网、接发球、扣球和抛球四种基本运动的检测，其ROC曲线的AUC平均达到0.9539。这比常规方法高0.014775。
For creating new tactics of sports like volleyball, the analysis of player motion in real games becomes more and more important. However, since motion data needed for the analysis is captured by human observation currently, an automatic capturing system from video camera is highly expected to gather many useful data easily. This paper proposes an action detection algorithm of volleyball players using motion features based on clustering and aggregation of body trajectories. Since the body trajectories of arms and legs are similar, the clustering utilizes shape, location and density of their trajectories. Furthermore, the clustered feature values are aggregated by means of their mean and variance. Experimental results by using the motion detection system based on the proposed algorithm show that it averagely attains 0.9539 AUC of the ROC curve for the detection of four basic motions (block, receive, spike and toss) from the volleyball game video captured by high-definition cameras. This is 0.014775 higher than conventional methods.