TY - JOUR A2 - Tolba, Amr AU - Li, Chenpu AU - Xing, Qianjian AU - Ma, Zhenguo AU - Zang, Ke PY - 2020 DA - 20/12/24 TI - MFCFSiam:随着深度学习的发展，基于卷积神经网络(CNNs)的跟踪器多年来在视觉跟踪方面取得了显著的成就。全连接Siamese网络(SiamFC)是这些跟踪器的典型代表。SiamFC设计了一个CNN的两分支架构，并将视觉跟踪作为一般的相似性学习问题进行建模。然而，它用于视觉跟踪的feature maps仅来自CNN的最后一层。这些特征包含高级语义信息，但缺乏足够详细的纹理信息。这意味着SiamFC跟踪器在存在其他同类别物体或目标与背景之间的对比度很低时倾向于漂移。为了解决这个问题，我们设计了一种新的跟踪算法，将相关滤波器跟踪器和SiamFC跟踪器结合到一个框架中。在这个框架中，相关滤波器跟踪器可以使用定向梯度直方图(HOG)和颜色名称(CN)特征来指导SiamFC跟踪器。该框架还包含一个评估标准，用于评估两个跟踪器的跟踪结果。 If this criterion finds the SiamFC tracker fails in some cases, our framework will use the tracking result from the correlation filter tracker to correct the SiamFC. In this way, the defects of SiamFC’s high-level semantic features are remedied by the HOG and CN features. So, our algorithm provides a framework which combines two trackers together and makes them complement each other in visual tracking. And to the best of our knowledge, our algorithm is also the first one which designs an evaluation criterion using correlation filter and zero padding to evaluate the tracking result. Comprehensive experiments are conducted on the Online Tracking Benchmark (OTB), Temple Color (TC128), Benchmark for UAV Tracking (UAV-123), and Visual Object Tracking (VOT) Benchmark. The results show that our algorithm achieves quite a competitive performance when compared with the baseline tracker and several other state-of-the-art trackers. SN - 1530-8669 UR - https://doi.org/10.1155/2020/6681391 DO - 10.1155/2020/6681391 JF - Wireless Communications and Mobile Computing PB - Hindawi KW - ER -