排球视频中结合似然度与粒子滤波的运动员跟踪方法  

Athlete Tracking Method Combined with Likelihood and Particle Filter in Volleyball Video

作　　者：朱守波[1] 黄石平[2] 

机构地区：[1]南京医科大学体育部,江苏南京210000 [2]南京医科大学信息与网络中心,江苏南京210000

出　　处：《湘潭大学自然科学学报》2017年第2期101-104,共4页Natural Science Journal of Xiangtan University

基　　金：国家自然科学基金项目(81302512)

摘　　要：为了解决排球视频中运动员重叠事件影响目标跟踪精度的问题,提出一种基于改进型粒子滤波的跟踪方法.首先,为每个跟踪目标标记一个不同颜色的标签,以此来检测重叠事件的发生,同时利用粒子滤波来跟踪目标.然后,当重叠事件发生时,根据目标的颜色似然度和距离似然度计算综合似然度,以此来避免粒子聚集到一个目标上.最后,根据位置预测模型来预测目标位置,实现目标的实时跟踪.实验结果表明,提出的方法能够对重叠事件具有鲁棒性,跟踪准确率达到了80%.In order to solve the problem that the overlap event affects the accuracy of target tracking in the volleyball video,a tracking method based on improved particle filter is proposed.First,each tracking target is tagged with a different color label to detect the occurrence of overlapping events,while particle tracking is used to track the target.Then,when the overlap event occurs,the composite likelihood is calculated from the target＇s color likelihood and distance likelihood,in order to avoid particle gathered on a target.Finally,the target location is predicted based on the position prediction model,so as to realize the realtime tracking of the target.The experimental results show that the proposed method is robust to overlap events and achieves 80%tracking accuracy.

关 键 词：排球视频 运动员跟踪 重叠事件 粒子滤波 综合似然度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]