Tracking articulated objects by learning intrinsic structure of motion

Tracking articulated objects by learning intrinsic structure of motion
复制标题

通过学习运动的内在结构来跟踪关节对象

DOI:
10.1016/j.patrec.2008.09.014
复制
发表时间:
2009-02
影响因子:
5.1
通讯作者:
Wu, Xinxiao
Wu, Xinxiao
中科院分区:
计算机科学3区
文献类型:
--
作者:
Jia, Yunde;Liang, Wei;Wu, Xinxiao

文献摘要

参考文献

被引文献

相似文献

在本文中,我们提出了一种新颖的降维方法,即时间邻域保留嵌入(TNPE),来学习铰接物体的低维固有运动流形。该方法通过保留隐藏在顺序数据点中的局部时间关系,同时学习嵌入流形和从图像特征空间到嵌入空间的映射。然后,跟踪被表述为根据学习的中心嵌入表示估计铰接对象的配置的问题。为了解决这个问题,我们将贝叶斯专家混合(BME)与高斯混合模型(GMM)相结合,建立从嵌入空间到配置空间的概率非线性映射。关节手和人体姿势跟踪的实验结果显示出在稳定性和准确性方面令人鼓舞的表现。
In this paper, we propose a novel dimensionality reduction method, temporal neighbor preserving embedding (TNPE), to learn the low-dimensional intrinsic motion manifold of articulated objects. The method simultaneously learns the embedding manifold and the mapping from an image feature space to an embedding space by preserving the local temporal relationship hidden in sequential data points. Then tracking is formulated as the problem of estimating the configuration of an articulated object from the learned central embedding representation. To solve this problem, we combine Bayesian mixture of experts (BME) with Gaussian mixture model (GMM) to establish a probabilistic non-linear mapping from the embedding space to the configuration space. The experimental result on articulated hand and human pose tracking shows an encouraging performance on stability and accuracy.
DOI: --
发表时间: 1994
期刊: --
影响因子: --
作者:
L. Xu;Michael I. Jordan;Geoffrey E. Hinton
通讯作者: L. Xu;Michael I. Jordan;Geoffrey E. Hinton
DOI: 10.1109/cvpr.2004.132
发表时间: 2004-06
期刊: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
影响因子: --
作者:
A. Elgammal;Chan-Su Lee
通讯作者: A. Elgammal;Chan-Su Lee
DOI: 10.1007/11744078_10
发表时间: 2006-05
期刊: --
影响因子: --
作者:
A. Thayananthan;R. Navaratnam;B. Stenger;P. Torr;R. Cipolla
通讯作者: A. Thayananthan;R. Navaratnam;B. Stenger;P. Torr;R. Cipolla
DOI: 10.1109/iccv.2005.167
发表时间: 2005-10
期刊: Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
影响因子: --
作者:
Xiaofei He;Deng Cai;Shuicheng Yan;HongJiang Zhang
通讯作者: Xiaofei He;Deng Cai;Shuicheng Yan;HongJiang Zhang