IEEE Trans Pattern Anal Mach Intell. 2019 May;41(5):1116-1130. doi: 10.1109/TPAMI.2018.2828817. Epub 2018 Apr 20.
Convolutional Neural Networks (CNNs) have been applied to visual tracking with demonstrated success in recent years. Most CNN-based trackers utilize hierarchical features extracted from a certain layer to represent the target. However, features from a certain layer are not always effective for distinguishing the target object from the backgrounds especially in the presence of complicated interfering factors (e.g., heavy occlusion, background clutter, illumination variation, and shape deformation). In this work, we propose a CNN-based tracking algorithm which hedges deep features from different CNN layers to better distinguish target objects and background clutters. Correlation filters are applied to feature maps of each CNN layer to construct a weak tracker, and all weak trackers are hedged into a strong one. For robust visual tracking, we propose a hedge method to adaptively determine weights of weak classifiers by considering both the difference between the historical as well as instantaneous performance, and the difference among all weak trackers over time. In addition, we design a Siamese network to define the loss of each weak tracker for the proposed hedge method. Extensive experiments on large benchmark datasets demonstrate the effectiveness of the proposed algorithm against the state-of-the-art tracking methods.
卷积神经网络（CNNs）近年来在视觉跟踪中得到了广泛应用，并取得了显著的成功。大多数基于 CNN 的跟踪器利用从特定层提取的分层特征来表示目标。然而，特定层的特征并不总是能够有效地将目标对象与背景区分开来，特别是在存在复杂干扰因素（例如，严重遮挡、背景杂波、光照变化和形状变形）的情况下。在这项工作中，我们提出了一种基于 CNN 的跟踪算法，该算法对冲来自不同 CNN 层的深度特征，以更好地区分目标对象和背景杂波。相关滤波器应用于每个 CNN 层的特征图来构建一个弱跟踪器，所有的弱跟踪器都被组合成一个强跟踪器。为了实现鲁棒的视觉跟踪，我们提出了一种对冲方法，通过同时考虑历史和当前性能之间的差异以及所有弱跟踪器随时间的差异，自适应地确定弱分类器的权重。此外，我们设计了一个孪生网络来为所提出的对冲方法定义每个弱跟踪器的损失。在大型基准数据集上的广泛实验表明，该算法在与最先进的跟踪方法的比较中具有有效性。
