Browse > Article

View-Invariant Body Pose Estimation based on Biased Manifold Learning  

Hur, Dong-Cheol (고려대학교 컴퓨터학과)
Lee, Seong-Whan (고려대학교 정보통신대학)
Abstract
A manifold is used to represent a relationship between high-dimensional data samples in low-dimensional space. In human pose estimation, it is created in low-dimensional space for processing image and 3D body configuration data. Manifold learning is to build a manifold. But it is vulnerable to silhouette variations. Such silhouette variations are occurred due to view-change, person-change, distance-change, and noises. Representing silhouette variations in a single manifold is impossible. In this paper, we focus a silhouette variation problem occurred by view-change. In previous view invariant pose estimation methods based on manifold learning, there were two ways. One is modeling manifolds for all view points. The other is to extract view factors from mapping functions. But these methods do not support one by one mapping for silhouettes and corresponding body configurations because of unsupervised learning. Modeling manifold and extracting view factors are very complex. So we propose a method based on triple manifolds. These are view manifold, pose manifold, and body configuration manifold. In order to build manifolds, we employ biased manifold learning. After building manifolds, we learn mapping functions among spaces (2D image space, pose manifold space, view manifold space, body configuration manifold space, 3D body configuration space). In our experiments, we could estimate various body poses from 24 view points.
Keywords
Pose Estimation; View Estimation; Manifold Learning; Supervised Learning;
Citations & Related Records
연도 인용수 순위
  • Reference
1 V. Balasubramanian and J. Ye, 'Biased Manifold Learning: A Framework for Person-Independent Head Pose Estimation,' Proc. IEEE Computer Vision and Pattern Recognition, Minneapolis, USA, pp.1-7, June 2007
2 Motion Golf 3-D Swing Analyzer: http://motiongolf.com
3 C. Lee and A. Elgammal, 'Modeling View and Posture Manifolds for Tracking,' Proc. IEEE International Conference on Computer Vision, Rio De Janeiro, Brazil, pp.1-8, October 2007   DOI
4 D. Specht, 'A General Regression Neural Network,' IEEE Trans. on Neural Networks, vol.2, no.6, pp.568-576, November 1991   DOI   ScienceOn
5 E. Murphy-Chutorian and M. Trivedi, 'Head Pose Estimation in Computer Vision: A Survey,' IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.31, no.4, pp.607-626, April 2009   DOI   ScienceOn
6 S. Roweis and L. Saul, 'Nonlinear Dimensionality Reduction by Locally Linear Embedding,' Science, vol.290, no.5500, pp.2323-2326, December 2000   DOI   PUBMED   ScienceOn
7 C. Lee and A. Elgammal, 'Simultaneous Inference of View and Body Pose using Torus Manifolds,' Proc. IEEE/IAPR International Conference on Pattern Recognition, Hong kong, China, pp.489-494, August 2006   DOI
8 Poser 7: http://my.smithmicro.com/dr/poser.html