• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Articulated motion and deformable objects >Compatible Particles for Part-Based Tracking
【24h】

Compatible Particles for Part-Based Tracking

机译：兼容的粒子用于基于零件的跟踪

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Particle Filter methods are one of the dominant tracking paradigms due to its ability to handle non-gaussian processes, multi-modality and temporal consistency. Traditionally, the exponential growth on the number of particles required (and therefore in the computational cost) with respect to the increase of the state space dimensionality means one of the major drawbacks for these methods. The problem of part based tracking, central nowadays, is hardly tractable within this framework. Several efforts have been made in order to solve this problem, as the appearance of hierarchical models or the extension of graph theory by means of the Nonparametric Belief Propagation. Our approach relies instead on the use of Auxiliary Particle Filters, models the relations between parts dynamically (without training) and introduces a compatibility factor to efficiently reduce the growth of the computational cost. We did run the experiments presented without using a priori information.
机译：粒子滤波方法由于其处理非高斯过程，多模态和时间一致性的能力而成为主要的跟踪范例之一。传统上，相对于状态空间维数的增长，所需粒子数的增长（以及计算成本的增长）意味着这些方法的主要缺点之一。如今，基于零件的跟踪问题在此框架内很难解决。为了解决这个问题，已经做出了一些努力，例如通过非参数置信度传播来出现层次模型或扩展图论。我们的方法取而代之地是使用辅助粒子滤波器，对零件之间的关系进行动态建模（无需训练），并引入一个兼容因数来有效减少计算成本的增长。我们确实在不使用先验信息的情况下运行了提出的实验。

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