东北大学学报(自然科学版) ›› 2025, Vol. 46 ›› Issue (9): 9-16.DOI: 10.12068/j.issn.1005-3026.2025.20240018

• 信息与控制 • 上一篇    下一篇

结合运动信息与双重注意力机制的两阶段SiamCAR跟踪算法

魏颖(), 张家鹏, 崔佳琦, 黄通   

  1. 东北大学 信息科学与工程学院,辽宁 沈阳 110819
  • 收稿日期:2024-01-17 出版日期:2025-09-15 发布日期:2025-12-03
  • 通讯作者: 魏颖
  • 作者简介:魏 颖(1968—),女,辽宁本溪人,东北大学教授,博士生导师.
  • 基金资助:
    辽宁省重点研发计划项目(2024JH2/102500015);国家自然科学基金资助项目(61871106);国家自然科学基金资助项目(62441231);中央高校基本科研业务费专项资金资助项目(N25BSS034)

Two-Stage SiamCAR Tracking Algorithm Combining Motion Information and Dual-attention Mechanism

Ying WEI(), Jia-peng ZHANG, Jia-qi CUI, Tong HUANG   

  1. School of Information Science & Engineering,Northeastern University,Shenyang 110819,China. cn
  • Received:2024-01-17 Online:2025-09-15 Published:2025-12-03
  • Contact: Ying WEI

摘要:

针对单目标跟踪中,因形变、运动模糊、遮挡以及背景干扰导致的跟踪框精度下降问题,特别是在背景干扰下易出现跟踪跳变及漂移问题,提出了一种结合运动信息和双重注意力机制的两阶段跟踪算法.第一阶段,使用带有双重注意力机制的SiamCAR跟踪器对当前帧的目标进行粗定位;第二阶段,利用像素级相似度运算构建边界框精细化模块,在低延迟情况下学习目标的细微特征以提升跟踪精度,并将基于外观特征得到的跟踪框与目标的运动轨迹信息相融合,以改善跟踪漂移及跳变问题.OTB100数据集上的实验结果表明,跟踪框的成功率和精度相比原来分别提高了4.6%和2.8%,在背景干扰下的成功率达到了69.6%.

关键词: 单目标跟踪, SiamCAR, 孪生网络, 神经网络, 注意力机制

Abstract:

In single-object tracking, the accuracy of the tracking bounding box is often compromised by factors such as deformation, motion blur, occlusion, and background interference. In particular, background interference frequently leads to tracking hopping and drift. To mitigate these issues, a two-stage tracking algorithm that integrated motion information with a dual-attention mechanism was proposed. In the first stage, a SiamCAR tracker with a dual-attention mechanism was employed to coarsely locate the target in the current frame. In the second stage, a refinement module of the bounding box was constructed using pixel-level similarity computations to learn the subtle features of the target under low-latency conditions, thereby enhancing the tracking accuracy. Finally, the tracking box obtained based on appearance features was fused with the target’s motion trajectory information to mitigate tracking drift and hopping. Experimental results on the OTB100 dataset indicate that the success rate and accuracy of the tracking box have improved by 4.6% and 2.8%, respectively, compared to the original. The success rate in the presence of background interference has reached 69.6%.

Key words: single object tracking, SiamCAR, Siamese network, neural network, attention mechanism

中图分类号: