基于MCMC粒子滤波的目标跟踪算法研究  

Research on Target Tracking Algorithm Based on MCMC Particle Filter

作　　者：高菲[1] 

机构地区：[1]宝鸡职业技术学院,宝鸡721000

出　　处：《计算机与数字工程》2017年第7期1323-1326,1331,共5页Computer & Digital Engineering

摘　　要：针对于贝叶斯框架下的视频目标跟踪算法的应用,结合MCMC粒子滤波算法的运算消耗,对运动模型、观测模型进行了研究,改进二值模型与颜色模型相结合的算法,颜色模型中的建模只采用其中的一通道来实现,减少了观测模型运算消耗,提高了运算速度。According to the application of video target tracking algorithm in the bayesian framework,in combination of opera-tion consumption of the MCMC particle filter algorithm, the motion model and observation model are studied. The algorithm of the bi-nary model and the color model combining is improved. Only one channel is used to realize in the modeling of the color model, which reduces the observation model operation cost and improves the operation speed.

关 键 词：粒子滤波算法 视频目标跟踪 颜色模型 二值模型 运动模型 

分 类 号：TN713[电子电信—电路与系统]