Learning Shape Trends: Parameter Estimation in Diffusions on Shape Manifolds

Learning Shape Trends: Parameter Estimation in Diffusions on Shape Manifolds
复制标题

学习形状趋势:形状流形扩散中的参数估计

DOI:
10.1109/cvprw.2017.101
复制
发表时间:
2017
期刊:
2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
影响因子:
--
通讯作者:
L. Younes
L. Younes
中科院分区:
--
文献类型:
--
作者:
Valentina Staneva;L. Younes

文献摘要

参考文献

被引文献

相似文献

学习形状的动力学是许多计算机视觉问题的核心:对象跟踪、变化检测、纵向形状分析、轨迹分类等。在这项工作中,我们解决了形状扩散过程的统计推断问题。我们在可变形地标的流形上制定了一般的 Itô 扩散,并提出了几种形状演化的漂移模型。我们推导了这些模型中未知参数的最大似然估计的显式公式,并在已知真实参数时证明了它们在模拟序列上的收敛特性。我们进一步讨论如何将这些模型扩展到更通用的非参数形状估计方法。
Learning the dynamics of shape is at the heart of many computer vision problems: object tracking, change detection, longitudinal shape analysis, trajectory classification, etc. In this work we address the problem of statistical inference of diffusion processes of shapes. We formulate a general Itô diffusion on the manifold of deformable landmarks and propose several drift models for the evolution of shapes. We derive explicit formulas for the maximum likelihood estimators of the unknown parameters in these models, and demonstrate their convergence properties on simulated sequences when true parameters are known. We further discuss how these models can be extended to a more general non-parametric approach to shape estimation.
亚黎曼流形上的亚拉普拉斯
DOI: 10.1007/s11118-016-9532-7
发表时间: 2016
期刊: Potential Analysis
影响因子: 1.1
作者:
Gordina, Maria;Laetsch, Thomas
通讯作者: Laetsch, Thomas