Open AccessACFT: adversarial correlation filter for robust tracking
Author(s) -
Huang Hanqiao,
Zha Yufei,
Zheng Meiyun,
Zhang Peng
Publication year - 2019
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2018.6672
Subject(s) - computer science , artificial intelligence , bittorrent tracker , robustness (evolution) , computer vision , filter (signal processing) , eye tracking , tracking (education) , feature (linguistics) , pattern recognition (psychology) , correlation , noise (video) , kalman filter , mathematics , image (mathematics) , psychology , pedagogy , biochemistry , chemistry , linguistics , philosophy , geometry , gene
Tracking based on correlation filters has demonstrated outstanding performance in recent visual object tracking studies and competitions. However, the performance is limited since the boundary effects are introduced by the intrinsic circular structure. In this study, a tracker, called adversarial correlation filter tracker (ACFT), is proposed to solve the above problem through Generative Adversarial Networks (GANs) that is specifically strong at producing realistic‐looking data from noise circumstances. Especially, a mask is generated by the GANs to assist the conventional correlation filter for the spatial regularisation. By overcoming the feature independence of current regularisation in another tracker, the GANs’ mask can be effectively used to identify the robust features for the target variations representation in the temporal domain. Also in the spatial domain, the background features can be substantially suppressed to obtain the optimisation filter for more reliable matching and updating. In verification, the authors evaluate the proposed tracker on the standard tracking benchmarks, and the experimental results show that their tracker outperforms favourably against other state‐of‐the‐art trackers in the measurements of accuracy and robustness.