基于Meanshift算法的110 m跨栏运动员助跑轨迹跟踪方法  

Run-up Track Tracking Method of 110-meter Hurdle Athletes Based on Meanshift Algorithm

作　　者：潘云磊 PAN Yunlei(Department of Physical Education,Wuhu Vocational and Technical College,Wuhu 241000,China)

机构地区：[1]芜湖职业技术学院体育教学部,安徽芜湖241000

出　　处：《长春大学学报》2022年第10期15-19,共5页Journal of Changchun University

基　　金：安徽省教育厅项目(SK2021A0928)

摘　　要：为充分发挥助跑对提升110 m跨栏成绩的促进作用,提出了基于Meanshift算法的110 m跨栏运动员助跑轨迹跟踪方法。使用摄像机采集110 m跨栏运动员助跑视频图像,创建110 m跨栏运动员助跑轨迹跟踪的运动学模型,实现110 m跨栏运动员助跑轨迹跟踪。实验结果表明:该方法对各帧图像内运动员位置的预测均方根误差始终低于0.35×10^(-5);该方法均具有较理想的助跑轨迹跟踪能力,且运动员的起跨前最佳成绩可达到8.5m/s。In order to give full play of promoting effect of run-up on improving the performance of 110 m hurdle,a method of track tracking of 110-meter hurdle athletes’run-up based on Meanshift algorithm is proposed.A camera is used to collect the video image of 110-meter hurdle athletes’run-up and a kinematic model is established to realize the track tracking.The experimental results show that the mean root square error of prediction of athletes’position in each frame is always lower than 0.35×10^(-5).This method has better effects for run-up track tracking,and the best performance of athletes before the starting of the stride can reach 8.5 m/s.

关 键 词：MEANSHIFT算法 110 m跨栏 助跑轨迹跟踪 

分 类 号：G822.6[文化科学—体育训练] TP391.41[文化科学—体育学]