Regularisation learning of correlation filters for robust visual tracking
Regularisation learning of correlation filters for robust visual tracking
复制标题
DOI：
10.1049/iet-ipr.2017.1043
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Min Jiang;Jianyu Shen;Jun Kong;Hongtao Huo
中科院分区：
文献类型：
--
作者：
Min Jiang;Jianyu Shen;Jun Kong;Hongtao Huo
近年来，基于核化相关滤波(KCF)的跟踪器引起了越来越多的关注，并在视觉目标跟踪领域的不同竞赛和基准中取得了非常令人信服的结果。然而，使用来自前一帧的简单线性过滤器组合的KCF的训练机制很容易导致误差累积。为了克服这一问题，作者提出了一种新的训练策略，该策略利用了所有以前的训练样本，并利用L1范数正则的稀疏性相关损失函数来处理KCF跟踪器中模板大小固定的问题，在跟踪过程中学习了单独的尺度滤波器来进行尺度估计。此外，融合了方向梯度直方图(HOG)和颜色特征等强大的特征，进一步提高了作者跟踪的鲁棒性。在各种具有挑战性的情况下的大量实验表明，该方法比几种最先进的跟踪算法具有更好的性能。
Recently, kernelised correlation filter (KCF)-based trackers aroused increasing interest and achieved extremely compelling results in different competitions and benchmarks in the field of visual object tracking. However, the training mechanism of the KCF that exploits simple linear combinations of filter from the previous frame easily cause error accumulation. To overcome this problem, the authors propose a novel training strategy that utilises all of the previous training samples, and a sparsity-related loss function regularised by the L1 norm to deal with the problem of the fixed template size in KCF trackers, a separate scale filter is learned for scale estimation during the tracking process. Moreover, powerful features that include histogram of oriented gradients (HOG) and colour features are integrated to further improve the robustness of the authors’ tracking. Extensive experiments in various challenging situations demonstrate that the proposed method performs favourably against several state-of-the-art tracking algorithms.