首页> 外文学位 >Statistical cue estimation for model-based shape and motion tracking.
【24h】

Statistical cue estimation for model-based shape and motion tracking.

机译:基于模型的形状和运动跟踪的统计提示估计。

获取原文
获取原文并翻译 | 示例

摘要

Vision-based tracking of moving objects is important in many applications, ranging from sports and medicine to security and recognition of human action. In this dissertation we discuss novel methods for statistical deformable model tracking. Our main contribution is a method to estimate the probability distributions of the observations in a deformable model tracking system. This method offers the compelling advantage that it does not require us to make many of the traditional assumptions about the underlying probability distributions of the cues. Despite this advantage, it still is fast, the run time overhead over non-statistical approaches is only 5–10%.; Our technique is based on the connection between affine forms, zonotopes, and Gaussian distributions. We use affine forms to bound and propagate confidences of image forces to confidences of the generalized forces in parameter space. Because its components are uniformly bounded, Lindeberg's theorem tells us that we can use a Gaussian distribution to approximate the random variable of the generalized force, described by the resulting affine form. The Berry-Esseen theorem provides an upper bound for the error in the optimal Gaussian approximation, and helps us to determine how many image forces are necessary to obtain a good Gaussian approximation. Unlike many other statistical methods our technique is suited for systems with large number of degrees of freedom.; We present two applications for the estimation of the cue distributions: automatic adaptive integration of different cues using a maximum likelihood estimator, and the distribution estimation of the observations for a predictive filter.; In this dissertation we also introduce the use directed acyclic graphs as powerful data structure to represent and implement deformable models. It allows us the creation of powerful and complex models with very few primitives.; Finally we show examples, evaluate and validate (both qualitatively and quantitatively) the benefits of our method in real face tracking experiments using a model with 11 degrees of freedom.
机译:基于视觉的运动对象跟踪在许多应用中都很重要,从运动和医学到安全性和对人类行为的识别,无所不包。本文讨论了统计可变形模型跟踪的新方法。我们的主要贡献是一种估计可变形模型跟踪系统中观测值的概率分布的方法。这种方法具有令人信服的优势,它不需要我们对线索的潜在概率分布进行许多传统的假设。尽管有这个优点,但它仍然很快,与非统计方法相比,运行时间开销仅为5–10%。我们的技术基于仿射形式,zonotopes 和高斯分布之间的联系。我们使用仿射形式将图像力的置信度约束并传播到参数空间中广义力的置信度。因为它的分量是有界的,所以 Lindeberg定理告诉我们,我们可以使用高斯分布来近似广义力的随机变量,并用由此产生的仿射形式来描述。 Berry-Esseen定理为最佳高斯近似中的误差提供了一个上限,并帮助我们确定要获得一个良好的高斯近似所需要的图像力。与许多其他统计方法不同,我们的技术适用于具有大量自由度的系统。我们提出了两种用于提示分布估计的应用程序:使用最大似然估计器对不同提示进行自动自适应积分,以及对预测过滤器的观测值进行分布估计。本文还介绍了使用有向无环图作为强大的数据结构来表示和实现可变形模型的方法。它使我们能够创建功能强大且复杂的模型,并且只包含很少的原语。最后,我们展示了示例,使用11个自由度的模型在真实人脸跟踪实验中(定性和定量地)评估和验证了我们方法的优势。

著录项

  • 作者

    Goldenstein, Siome Klein.;

  • 作者单位

    University of Pennsylvania.;

  • 授予单位 University of Pennsylvania.;
  • 学科 Computer Science.
  • 学位 Ph.D.
  • 年度 2002
  • 页码 72 p.
  • 总页数 72
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 自动化技术、计算机技术;
  • 关键词

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