Scholarlink

<p>Visual object tracking is crucial for numerous applications ranging from smartphones to autonomous vehicles. However, the impact of input noise on tracking performance remains underexplored. This paper presents a lightweight neural network module designed to enhance the robustness of 2D tracking methods against various types of noise. By performing image-to-image translation, the proposed robust tracking module (RTM) standardizes the operational space of tracking algorithms, thereby improving their resilience. Experimental results on benchmark datasets demonstrate the effectiveness of RTM in mitigating performance degradation caused by noise. Additionally, we introduce an evaluation toolkit that facilitates the assessment of tracking robustness against common noise types. The source code of the proposed method is available at <a href="https://github.com/iason1907/RTM">https://github.com/iason1907/RTM</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing visual object tracking robustness through a lightweight denoising module

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月18日

查看全文
  • Iason Karakostas,
  • Vasileios Mygdalis,
  • Nikos Nikolaidis,
  • Ioannis Pitas

摘要

Visual object tracking is crucial for numerous applications ranging from smartphones to autonomous vehicles. However, the impact of input noise on tracking performance remains underexplored. This paper presents a lightweight neural network module designed to enhance the robustness of 2D tracking methods against various types of noise. By performing image-to-image translation, the proposed robust tracking module (RTM) standardizes the operational space of tracking algorithms, thereby improving their resilience. Experimental results on benchmark datasets demonstrate the effectiveness of RTM in mitigating performance degradation caused by noise. Additionally, we introduce an evaluation toolkit that facilitates the assessment of tracking robustness against common noise types. The source code of the proposed method is available at https://github.com/iason1907/RTM.