IEEE Trans Cybern. 2019 Jan;49(1):146-158. doi: 10.1109/TCYB.2017.2768570. Epub 2017 Nov 14.
Convolutional neural networks can efficiently exploit sophisticated hierarchical features which have different properties for visual tracking problem. In this paper, by using multilayer convolutional features jointly and constructing a scale pyramid, we propose an online scale adaptive tracking method. We construct two separate correlation filters for translation and scale estimations. The translation filters improve the accuracy of target localization by a weighted fusion of multiple convolutional layers. Meanwhile, the separate scale filters achieve the optimal and fast scale estimation by a scale pyramid. This design decreases the mutual errors of translation and scale estimations, and reduces computational complexity efficiently. Moreover, in order to solve the problem of tracking drifts due to the severe occlusion or serious appearance changes of the target, we present a new adaptive and selective update mechanism to update the translation filters effectively. Extensive experimental results show that our proposed method achieves the excellent overall performance compared with the state-of-the-art methods.
卷积神经网络可以有效地利用复杂的层次特征，这些特征对于视觉跟踪问题具有不同的性质。在本文中，我们通过联合使用多层卷积特征并构建一个尺度金字塔，提出了一种在线尺度自适应跟踪方法。我们为平移和尺度估计构建了两个独立的相关滤波器。平移滤波器通过对多个卷积层的加权融合来提高目标定位的准确性。同时，通过尺度金字塔，独立的尺度滤波器实现了最优和快速的尺度估计。这种设计减少了平移和尺度估计的相互误差，有效地降低了计算复杂度。此外，为了解决由于目标的严重遮挡或严重外观变化导致的跟踪漂移问题，我们提出了一种新的自适应和选择性更新机制，有效地更新平移滤波器。广泛的实验结果表明，与最先进的方法相比，我们提出的方法具有优异的整体性能。
