当前位置: X-MOL 学术J. Electron. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Adaptive decision-level fusion and complementary mining for visual object tracking with deeper networks
Journal of Electronic Imaging ( IF 1.1 ) Pub Date : 2020-08-25 , DOI: 10.1117/1.jei.29.4.043024
Xiaoyan Meng 1 , Yangzhou Chen 1 , Le Xin 1
Affiliation  

Abstract. Multiple region proposal networks (RPNs) have been recently combined with the Siamese network with deeper backbone networks for tracking and shown excellent accuracy with high efficiency. Although the destruction of the strict translation invariance caused by network padding in the original ResNet-50 is solved by a custom sampling strategy, its impact is not eliminated from the network structure itself, and the multilayer feature fusion is insufficient. To this end, we propose an object tracking framework based on SiamRPN with the deeper backbone networks and cascaded RPN (D-CRPN). First, we exploit the cropping-inside residual units for reforming ResNet-50 to break the spatial invariance restriction and train the robust backbone networks for visual tracking. Then, the feature transfer blocks are proposed to achieve the effective integration of the outputs of multiple blocks in a specific network stage. Finally, to improve the robustness of our tracker, we present a quality measure for the synthetic response maps of RPN modules and then use it to calculate the adaptive weights for the linear weighting method. The extensive evaluation performed on OTB100, VOT2016, and VOT2018 benchmark datasets demonstrates that the proposed D-CRPN tracker outperforms most of the state-of-the-art approaches while maintaining real-time tracking speed.

中文翻译:

具有更深网络的视觉对象跟踪的自适应决策级融合和互补挖掘

摘要。多区域提议网络(RPN)最近与具有更深骨干网络的连体网络相结合,用于跟踪并显示出高效率的出色准确性。虽然通过自定义采样策略解决了原始 ResNet-50 中网络填充导致的严格平移不变性的破坏,但其影响并未从网络结构本身中消除,多层特征融合不足。为此,我们提出了一种基于 SiamRPN 的对象跟踪框架,具有更深的骨干网络和级联 RPN(D-CRPN)。首先,我们利用裁剪内部残差单元来改造 ResNet-50,以打破空间不变性限制并训练强大的骨干网络进行视觉跟踪。然后,提出特征转移块是为了在特定网络阶段实现多个块的输出的有效集成。最后,为了提高跟踪器的鲁棒性,我们提出了 RPN 模块的合成响应图的质量度量,然后使用它来计算线性加权方法的自适应权重。对 OTB100、VOT2016 和 VOT2018 基准数据集进行的广泛评估表明,所提出的 D-CRPN 跟踪器在保持实时跟踪速度的同时优于大多数最先进的方法。
更新日期:2020-08-25
down
wechat
bug