足球带球过人脚步移动弧线轨迹实时提取仿真

Soccer Ball Passing After They Feet Moving Arc Extracted Simulation in Real Time

对足球带球过人的脚步移动弧线轨迹进行实时提取,能够有效提高足球运动员比赛成绩。对带球过人脚步移动弧线轨迹的提取,需要首先建立带球过人脚步移动模型获取其内外参数,分离轨迹关键特征点进行最优匹配,完成轨迹的实时提取。传统方法首先预测弧线当前时刻每个跟踪概率密度函数,再将检测状态融入轨迹跟踪器中,但忽略了轨迹关键特征点的最优匹配,导致提取精度低。提出轨迹聚类的轨迹实时提取方法。先用二值化方法建立脚步移动模型,对模型进行跟踪,获取摄像机内外参数,分离出脚步所在区域的移动轨迹关键特征点,进行轨迹聚类,对移动弧线轨迹前后帧的特征点做最优匹配,完成对移动弧线轨迹实时的提取。仿真证明,所提方法具有较高的鲁棒性,且具有较好的动作概括力。

ABSTRACT： A real-time extraction method of feet moving arc trajectory for trail clustering is proposed. First of all, a footstep movement model with binaryzation method is built, thus intrinsic and extrinsic parameters of camera are ob- tained, and then key feature points of movement trail of footstep area are separated to carry out trail clustering. At last, the optimal matching for feature point of front and rear frames of movement are trail are performed, thus real- time extraction of movement are trail is completed. The simulation results demonstrate that this method has high ro- bustness and good action generalization.