Computer Engineering and Applications ›› 2020, Vol. 56 ›› Issue (6): 153-158.DOI: 10.3778/j.issn.1002-8331.1811-0367

Previous Articles     Next Articles

Margin-Maximized Correlation-Filter Based Tracking Method Advanced by Mask Mechanism

FENG Xuegang, ZHOU Dake, YANG Xin   

  1. College of Automatic Engineering, Nanjing Unversity of Aeronautics and Astronautics, Nanjing 211100, China
  • Online:2020-03-15 Published:2020-03-13



  1. 南京航空航天大学 自动化学院,南京 211100


In correlation filter-based tracking methods, redundant dense samples generated by cyclic shifts suffer from both boundary effect and unbalanced categories, which mainly upper bound the training performance. To figure out the two above problems, a margin-maximized correlation filter advanced by mask mechanism is proposed, where the purified samples can be trained in a more effective way. A dual variable is used to convert the original margin maximization problem into a loss minimization one. The final advanced correlation filter can be iteratively solved out by the alternating direction methods of multipliers. Plenty of experimental results indicate that the proposed algorithm can significantly improve the correlation filter. Compared with other tracking algorithms, the proposed tracking algorithm has obvious advantages in speed and location accuracy.

Key words: object tracking, correlation filter, boundary effect, margin maximization



关键词: 目标跟踪, 相关滤波, 边界效应, 最大化间隔