计算机应用 ›› 2012, Vol. 32 ›› Issue (02): 504-506.DOI: 10.3724/SP.J.1087.2012.00504

• 图形图像技术 • 上一篇    下一篇

改进的均值漂移和粒子滤波混合跟踪方法

李科,徐克虎,黄大山   

  1. 装甲兵工程学院 控制工程系,北京 100072
  • 收稿日期:2011-07-14 修回日期:2011-09-26 发布日期:2012-02-23 出版日期:2012-02-01
  • 通讯作者: 李科
  • 作者简介:李科(1985-),男,湖南湘潭人,硕士研究生,CCF会员,主要研究方向:目标跟踪;
    徐克虎(1963-),男,安徽蚌埠人,教授,博士,主要研究方向:系统仿真;
    黄大山(1987-),男,黑龙江哈尔滨人,硕士研究生,主要研究方向:模式识别。
  • 基金资助:
    国防预研基金资助项目(9140A09050708JB3503)

Improved object tracking method based on mean shift and particle filter

LI Ke,XU Ke-hu,HUANG Da-shan   

  1. Department of Control Engineering,Academy of the Armored Force Engineering, Beijing 100072, China
  • Received:2011-07-14 Revised:2011-09-26 Online:2012-02-23 Published:2012-02-01
  • Contact: LI Ke

摘要: 为提高粒子滤波视觉目标跟踪算法的准确性和实时性,提出一种基于均值漂移和粒子滤波的混合跟踪算法。将相异性较小的粒子进行聚类,利用均值漂移算法迭代各个聚类中的代表点,通过减少参与均值漂移迭代的粒子数来降低运算复杂度;根据跟踪情况自适应调整采样粒子数目和过程噪声分布,以提高跟踪精度和减少运算时间。实验结果表明,所提算法平均每帧计算时间不到传统混合跟踪法的一半,而且跟踪精度也有所提高。

关键词: 目标跟踪, 均值漂移, 粒子滤波, 重采样, 过程噪声

Abstract: To improve the accuracy and real-time performance of particle filter algorithm for tracking vision object, an improved algorithm in combination with mean shift and particle filter was proposed. Similar particles were clustered, and representative particles were iterated in each cluster by using mean shift algorithm. Then computation complexity was reduced by fewer mean shift iterative particles. Particle number and process noise distribution were adjusted adaptively based on tracking condition to improve tracking accuracy and reduce computation complexity. The experimental results prove the superiority of the proposed method, the average of each frame' operation time of this method is less than half of classic bybrid algorithm, and its computation complexity is also less than classic bybrid algorithm.

Key words: object tracking, mean shift, particle filter, resampling, process noise

中图分类号: