论文标题
使用深度特征和相关过滤器的粗到限制对象跟踪
Coarse-to-Fine Object Tracking Using Deep Features and Correlation Filters
论文作者
论文摘要
在过去的几年中，深度学习跟踪器取得了刺激的结果，同时带来了有趣的想法来解决跟踪问题。这种进步主要是由于使用大图像数据库上的深层卷积神经网络（CNN）获得的学习深度特征。但是，由于CNN最初是为图像分类而开发的，因此由其深层提供的外观建模可能不足以进行跟踪任务。实际上，此类功能代表了高级信息，这与对象类别相比，而不是与对象的特定实例相关。受这一观察结果的动机，以及歧视性相关过滤器（DCF）可能提供免费的低级信息，我们会提出利用这两种方法的新颖跟踪算法。我们将跟踪任务作为两个阶段过程。首先，我们利用深度特征的概括能力来估计目标翻译，同时确保不变性到外观变化。然后，我们利用相关过滤器的判别能力，以精确定位跟踪对象。此外，我们设计了一种更新控制机制，以学习外观变化，同时避免模型漂移。我们在对象跟踪基准测试上评估了所提出的跟踪器。实验结果表明，我们的算法的鲁棒性，该算法对基于CNN和基于DCF的跟踪器的性能良好。代码可在以下网址找到：https：//github.com/ahmedzgaren/coarse-to-fine-tracker
During the last years, deep learning trackers achieved stimulating results while bringing interesting ideas to solve the tracking problem. This progress is mainly due to the use of learned deep features obtained by training deep convolutional neural networks (CNNs) on large image databases. But since CNNs were originally developed for image classification, appearance modeling provided by their deep layers might be not enough discriminative for the tracking task. In fact,such features represent high-level information, that is more related to object category than to a specific instance of the object. Motivated by this observation, and by the fact that discriminative correlation filters(DCFs) may provide a complimentary low-level information, we presenta novel tracking algorithm taking advantage of both approaches. We formulate the tracking task as a two-stage procedure. First, we exploit the generalization ability of deep features to coarsely estimate target translation, while ensuring invariance to appearance change. Then, we capitalize on the discriminative power of correlation filters to precisely localize the tracked object. Furthermore, we designed an update control mechanism to learn appearance change while avoiding model drift. We evaluated the proposed tracker on object tracking benchmarks. Experimental results show the robustness of our algorithm, which performs favorably against CNN and DCF-based trackers. Code is available at: https://github.com/AhmedZgaren/Coarse-to-fine-Tracker
