School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China.
The State Key Laboratory of Software Engineering, School of Computer, Wuhan University, China.
Neural Netw. 2020 Dec;132:364-374. doi: 10.1016/j.neunet.2020.09.011. Epub 2020 Sep 24.
Existing regression based tracking methods built on correlation filter model or convolution model do not take both accuracy and robustness into account at the same time. In this paper, we propose a dual-regression framework comprising a discriminative fully convolutional module and a fine-grained correlation filter component for visual tracking. The convolutional module trained in a classification manner with hard negative mining ensures the discriminative ability of the proposed tracker, which facilitates the handling of several challenging problems, such as drastic deformation, distractors, and complicated backgrounds. The correlation filter component built on the shallow features with fine-grained features enables accurate localization. By fusing these two branches in a coarse-to-fine manner, the proposed dual-regression tracking framework achieves a robust and accurate tracking performance. Extensive experiments on the OTB2013, OTB2015, and VOT2015 datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods.
现有的基于相关滤波模型或卷积模型的回归跟踪方法不能同时兼顾准确性和鲁棒性。在本文中，我们提出了一种双回归框架，包括一个判别性的全卷积模块和一个细粒度的相关滤波器组件，用于视觉跟踪。使用硬负挖掘进行分类训练的卷积模块确保了所提出的跟踪器的判别能力，这有助于处理几个具有挑战性的问题，如剧烈变形、干扰物和复杂背景。基于浅层特征和细粒度特征构建的相关滤波器组件实现了精确的定位。通过以粗到精的方式融合这两个分支，所提出的双回归跟踪框架实现了鲁棒和准确的跟踪性能。在 OTB2013、OTB2015 和 VOT2015 数据集上的广泛实验表明，所提出的算法优于最先进的方法。
