基于改进的粒子滤波算法的目标跟踪  

Target Tracking Based on Improved Particle Filter Algorithm

作　　者：闫嘉琪 李蕊[1] 沈晓斌[1] 

机构地区：[1]天津冶金职业技术学院机械工程系,天津300400

出　　处：《测控技术》2014年第11期53-56,共4页Measurement & Control Technology

摘　　要：将均值漂移算法与粒子滤波有效结合,通过比较粒子的权重,对粒子进行重采样,剔除大量的权重小的粒子,再加入均值漂移算法对粒子进行聚类,使用很少的粒子就能完全描述目标的状态信息,克服了粒子滤波计算量大的缺点,在实时监控中大大提高了跟踪效率。实验证明,该算法具有较好的实时性、鲁棒性和准确性。Different particles＇ weighted values are compared through effective integrating mean-shift algorithm and particle filter,these particles are resampled.The particles with small weighted value are eliminated to cluster them with mean-shift algorithm,so that the status information can be described by using a few particles.This method can overcome the shortcoming of particle filter calculation,and the tracking efficiency is greatly improved in real-time monitoring.The experiment shows that this method can bring good performances such as real-time,robustness and accuracy.

关 键 词：粒子滤波 均值漂移 目标跟踪 重采样 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]