Acta Optica Sinica, Volume. 37, Issue 5, 515001(2017)

Multi-Scale Correlation Filtering Tracker Based on Adaptive Feature Selection

Shen Qiu, Yan Xiaole, Liu Linfeng, Kong Fanqiang, and Wang Dandan
Author Affiliations
  • [in Chinese]
  • show less

    Recently, the correlation filter-based trackers have aroused increasing interest because of their good performance and high efficiency. A multi-scale correlation filtering tracker based on adaptive feature selection is presented. Firstly, we extract three complementary features to learn three independent filter models. By comparing the response maps, we evaluate the tracking performance of each feature, and then adaptively select the most representative feature for tracking. Secondly, to better handle occlusions and drifts, we improve the online model update strategy by setting peak response threshold as a criterion. Furthermore, we learn a separate filter model for scale estimation. The experimental results show that the proposed tracker achieves better accuracy compared with state-of-the-art correlation filter-based trackers and other popular trackers when running at 53.12 frame/s.

    Tools

    Get Citation

    Copy Citation Text

    Shen Qiu, Yan Xiaole, Liu Linfeng, Kong Fanqiang, Wang Dandan. Multi-Scale Correlation Filtering Tracker Based on Adaptive Feature Selection[J]. Acta Optica Sinica, 2017, 37(5): 515001

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Machine Vision

    Received: Oct. 21, 2016

    Accepted: --

    Published Online: May. 5, 2017

    The Author Email:

    DOI:10.3788/aos201737.0515001

    Topics