北京航空航天大学学报 ›› 2018, Vol. 44 ›› Issue (1): 151-159.doi: 10.13700/j.bh.1001-5965.2017.0038

• 论文 • 上一篇    下一篇

基于傅里叶域卷积表示的目标跟踪算法

朱日东, 杨小远, 王敬凯   

  1. 北京航空航天大学 数学与系统科学学院, 北京 100083
  • 收稿日期:2017-01-18 修回日期:2017-04-07 出版日期:2018-01-20 发布日期:2017-05-16
  • 通讯作者: 杨小远 E-mail:xiaoyuanyang@vip.163.com
  • 作者简介:朱日东,男,博士研究生。主要研究方向:目标跟踪;杨小远,女,博士,教授,博士生导师。主要研究方向:应用调和分析与图像处理;王敬凯,男,博士研究生。主要研究方向:多源遥感图像融合。
  • 基金资助:
    国家自然科学基金(61671002);北京市自然科学基金(4152029)

Convolution representation-based object tracking algorithm in Fourier domain

ZHU Ridong, YANG Xiaoyuan, WANG Jingkai   

  1. School of Mathematics and Systems Science, Beijing University of Aeronautics and Astronautics, Beijing 100083, China
  • Received:2017-01-18 Revised:2017-04-07 Online:2018-01-20 Published:2017-05-16

摘要: 针对目标跟踪问题,提出基于傅里叶域卷积表示的目标跟踪算法,将目标跟踪问题转化为卷积表示模型,通过求解最优滤波器,得到对目标函数的最佳表示,可以实现快速鲁棒的跟踪。多通道卷积表示模型在傅里叶域等价于求解线性方程的最佳近似解。首先,通过广义逆理论求得该方程的最优通解,给出一般滤波器的表示形式;然后,利用前一时刻的滤波器和当前特征模板生成当前滤波器,利用满秩算法快速求解广义逆;最后,在位移和尺度上更新、应用该滤波器。在目标跟踪基准(OTB)数据库中的大量实验表明,本文算法比当前部分较为先进的跟踪算法具有更好的表现,并提供了更加灵活多样的滤波器设计。

关键词: 目标跟踪, 卷积表示, Moore-Penrose广义逆, 傅里叶变换, 最佳逼近

Abstract: A novel object tracking algorithm based on convolution representation in Fourier domain is proposed for object tracking. Object tracking question can be treated as a convolution representation model. By finding the best filters, which reconstruct the target function with minimum loss, fast and robust object tracking can be realized. When the optimal multi-channel convolution representation model is mapped to the Fourier domain, it is equal to solving the least squares solution to linear equations. First, all solutions of the system of linear equations can be expressed through the theory of pseudo inverse, which provide a general format of convolution filters. Then, filters updated in the previous frame and feature templates extracted from current frame are used to generate current filters, and the pseudo inverse can be obtained fast through the full rank algorithm. Finally, tracking filters are updated and applied in both translation and scale. Experimental results on the object tracking benchmark (OTB) database show that our algorithm performs better than some state-of-the-art tracking methods in terms of accuracy and offers a general format to design filters.

Key words: object tracking, convolution representation, Moore-Penrose pseudo inverse, Fourier transform, optimal approximation

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发