作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 开发研究与工程应用 • 上一篇    下一篇

基于均值漂移的改进目标跟踪算法

刘天键,邱立达,张宁   

  1. (闽江学院物理学与电子信息工程系,福州 350108)
  • 收稿日期:2015-03-03 出版日期:2015-09-15 发布日期:2015-09-15
  • 作者简介:刘天键(1975-),男,副教授、博士,主研方向:目标检测与跟踪;邱立达、张宁,讲师、硕士。
  • 基金资助:

    福建省教育厅基金资助项目(JA12263,JB11127);福州市科技合作基金资助项目(2013-G-86)。

Improved Object Tracking Algorithm Based on Mean Shift

LIU Tianjian,QIU Lida,ZHANG Ning   

  1. (Department of Physics and Electronic Information Engineering,Minjiang University,Fuzhou 350108,China)
  • Received:2015-03-03 Online:2015-09-15 Published:2015-09-15

摘要:

在可视化跟踪过程中目标窗经常会由于遮挡、光照、姿势等变化而发生跟踪漂移,影响目标跟踪的准确性和稳定性。为解决该问题,提出一种基于图层的离散域均值漂移算法,在离散域提取基于核的直方图作为目标模型,并对离散分区中的目标函数进行平滑以避免寻优搜索陷入局部极小值,从而提高目标跟踪性能。实验结果表明,与多示例学习算法相比,该算法的跟踪精度提高了16%,具有更好的实时性和鲁棒性。

关键词: 目标跟踪, 目标表示, 离散域模型, 均值漂移, 迭代寻优

Abstract:

In the process of visual tracking,target window is always drifted for the illumination light change,deformation and poses change which affect the accuracy and robust tracking performance.To solve this problem,this paper proposes a novel Mean Shift(MS) algorithm based on picture layer which represents target model by the kernel histogram in the discrete fields.In order to improve the tracking performance,the objective function is smoothed to avoid falling into the local minimum in the search procedure.Experimental results show that the tracking precision of proposed algorithm increases by 16% compared with Multiple Instance Learning(MIL) algorithm,and it has better real-time and robustness.

Key words: object tracking, object representation, discrete domain model, Mean Shift(MS), iterative optimization

中图分类号: