Visual Object Tracking via Cascaded RPN Fusion and Coordinate Attention
Visual Object Tracking via Cascaded RPN Fusion and Coordinate Attention
复制标题
通过级联 RPN 融合和坐标注意进行视觉对象跟踪
DOI：
10.32604/cmes.2022.020471
复制
发表时间：
2022-04-21
影响因子：
2.4
通讯作者：
Kuang, Lidan
中科院分区：
文献类型：
--
作者：
Zhang, Jianming;Wang, Kai;Kuang, Lidan
近年来，基于连体体的跟踪器在目标跟踪方面取得了优异的成绩。然而，物体在运动过程中的高速和变形给跟踪带来了困难。因此，我们将级联区域-建议-网络（RPN）融合和协调注意结合到Siamese跟踪器中。提出的网络框架由三个部分组成：特征提取子网络、坐标关注块和级联RPN块。我们利用坐标注意块将位置信息嵌入到通道注意中，在保持通道关联的同时建立长期的空间位置依赖关系。因此，通过坐标注意块来增强不同层的特征。然后我们将这些特征分别发送到级联RPN中进行分类和回归。根据两种分类和回归结果，得到目标的最终位置。为了验证该方法的有效性，我们在OTB100、VOT2016、UAV123和GOT-10k数据集上进行了综合实验。与其他先进的跟踪器相比，所提出的跟踪器性能良好，可以实时运行。
Recently, Siamese-based trackers have achieved excellent performance in object tracking. However, the high speed and deformation of objects in the movement process make tracking difficult. Therefore, we have incorporated cascaded region-proposal-network (RPN) fusion and coordinate attention into Siamese trackers. The proposed network framework consists of three parts: a feature-extraction sub-network, coordinate attention block, and cascaded RPN block. We exploit the coordinate attention block, which can embed location information into channel attention, to establish long-term spatial location dependence while maintaining channel associations. Thus, the features of different layers are enhanced by the coordinate attention block. We then send these features separately into the cascaded RPN for classification and regression. According to the two classification and regression results, the final position of the target is obtained. To verify the effectiveness of the proposed method, we conducted comprehensive experiments on the OTB100, VOT2016, UAV123, and GOT-10k datasets. Compared with other state-of-the-art trackers, the proposed tracker achieved good performance and can run at real-time speed.