基于KCF算法的足球运动员体能录像跟踪技术研究  

The Video Analysis of the Players' Physical Fitness during the Soccer Competition Based on the Kernelized Correlation Filter

作　　者：李震[1] 毛丽娟[1] 盛斌[2] 孟夏 LI Zhen;MAO Lijuan;SHENG Bin;MENG Xia(School of Physical Education ＆ Sports Training,Shanghai University of Sport,Shanghai 200438,China;Department of Computer Science and Engineering,Shanghai Jiao Tong University,Shanghai 200240,China)

机构地区：[1]上海体育学院体育教育训练学院,上海200438 [2]上海交通大学计算机科学与工程系,上海200240

出　　处：《上海体育学院学报》2018年第4期75-80,共6页Journal of Shanghai University of Sport

基　　金：上海市科委课题(15490503200)

摘　　要：基于对现有视频跟踪技术的分析,提出一种基于KCF算法的多视角、多目标足球跟踪技术,通过调整学习率和样本范围提高准确率,并结合多视角视频信息加权定位球员位置。测试结果显示:该方法能够提高抗遮挡能力,保证跟踪处理速度,减少相似跟踪目标带来的误差,解决足球比赛中录像跟踪的多目标跟踪问题。Through the study of the current video tracking technology,a newalgorithm,named Kernelized Correlation Filter with multi-dimensional video analysis,can increase the accuracy by adjusting the study rate and samples＇ range,and track the players＇ movement combining with the weighted video information. The results showthat the method can improve the blocking-resistance ability,guarantee the tracking processing speed,and reduce the tracking error of the similar target,which can better solve the soccer video tracking problem of more targets tracking.

关 键 词：足球比赛 运动员体能 KCF算法 录像跟踪 目标跟踪 

分 类 号：G807[文化科学—体育训练]