具有动态弹性稀疏表示的鲁棒目标跟踪算法
作者:
作者单位:

北京理工大学 自动化学院

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:


Dynamic Elastic Net Sparse Representation Robust Visual Tracking
Author:
Affiliation:

School of Automation, Beijing Institute of Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    目标跟踪问题中目标所在环境的变化对跟踪效果有较大影响。针对这一问题,本文提出了一种基于弹性网结构的稀疏表示模型,并在粒子滤波框架下设计了一种应用稀疏表示模型的抗干扰动态弹性网目标跟踪算法。其次,本文设计了一种根据环境变化程度动态更新稀疏表示模型参数的方法,以克服光照变化等干扰对算法跟踪质量的影响。此外,本文算法通过使用各向异性核函数计算各候选区域为跟踪目标所在位置的概率提高了跟踪算法的准确性,并改进了字典模板更新方法,确保模板更新的准确性与及时性,保证了跟踪质量。经实验验证,本文提出的动态弹性网跟踪算法与其它跟踪算法相比,在光照等扰动下有更好的跟踪效果,在遮挡及快速运动等情况下,也能有效保证跟踪精度。

    Abstract:

    In visual tracking, the target"s environment has a significant influence on the tracking result. To solve this problem, we proposed a sparse representation model based on the elastic net and designed an anti-jamming visual tracking algorithm under the particle filter framework. To overcome the influence of light change and other disturbances on the tracking result, we developed a method to dynamically update sparse representation model parameters according to the environment change. Besides, using the anisotropic kernel function to calculate the probability that each candidate region is the tracking target"s location, the algorithm in this paper improves the tracking algorithm"s accuracy. Furthermore, we improved the dictionary template updating method to ensure the accuracy and timeliness of template updating and ensure the tracking quality. Experimental results showed that compared with other tracking algorithms, the dynamic elastic network tracking algorithm proposed in this paper has a better tracking effect under disturbance, such as illumination. Moreover, our algorithm can virtually guarantee tracking accuracy under occlusion and fast motion.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-06-30
  • 最后修改日期:2021-06-29
  • 录用日期:2020-09-25
  • 在线发布日期: 2020-11-01
  • 出版日期: