首页> 外文会议>International symposium on multispectral image processing and pattern recognition >Discussion among Different Methods of Updating Model Filter in Object Tracking
【24h】

Discussion among Different Methods of Updating Model Filter in Object Tracking

机译:目标跟踪中更新模型过滤器的不同方法之间的讨论

获取原文

摘要

Discriminative correlation filters (DCF) have recently shown excellent performance in visual object tracking area. In this paper we summarize the methods of updating model filter from discriminative correlation filter (DCF) based tracking algorithms and analyzes similarities and differences among these methods. We deduce the relationship among updating coefficient in high dimension (kernel trick), updating filter in frequency domain and updating filter in spatial domain, and analyze the difference among these different ways. We also analyze the difference between the updating filter directly and updating filter's numerator (object response power) with updating filter's denominator (filter's power). The experiments about comparing different updating methods and visualizing the template filters are used to prove our derivation.
机译:判别相关滤波器(DCF)最近在视觉对象跟踪区域显示了出色的性能。在本文中,我们总结了从基于判别相关滤波器(DCF)的跟踪算法中更新模型滤波器的方法,并分析了这些方法之间的异同。我们推导了高维更新系数(核技巧),频域更新滤波器和空间域更新滤波器之间的关系,并分析了这些不同方式之间的差异。我们还分析了直接更新过滤器与使用更新过滤器的分母(过滤器的功率)更新过滤器的分子(对象响应功率)之间的差异。通过比较不同的更新方法和可视化模板过滤器的实验来证明我们的推导。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号