一种基于多信息融合的粒子滤波跟踪算法  

A particle filter tracking algorithm based on multi-information fusion

作　　者：陈聪[1] 闵华清[1] 罗荣华[1] 

机构地区：[1]华南理工大学计算机科学与工程学院,广东广州510640

出　　处：《信息化纵横》2009年第10期59-62,65,共5页

摘　　要：将颜色和灰度梯度这两种信息融合进粒子滤波跟踪器中,采用多块颜色模型和目标模板更新策略等技术,克服了依赖单一信息源而造成跟踪困难的问题,而且在跟踪的精确度和准确率上都有所突破。实验表明,该粒子滤波跟踪算法对多种干扰都有较强的抵抗能力。We present a particale filter （PF） algorithm to target tracking that fuses color and Gray gradient information, applying muti-color model and target template update strategy to the algortihm.it not only overcomes the instability brought by using a single measurement source, but also improves the accuracy and precision.The experimental results show that the algorithm has a wide rang of resistance to many kinds of interferenc .

关 键 词：灰度梯度信息 颜色特征 粒子滤波 补偿策略 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]