A Framework for Modeling the Appearance of 3D Articulated Figures

Authors:
Hedvig Sidenbladh;Fernando de la Torre;Michael J. Black
Affiliations:
-;-;-
Venue:
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Year:
2000

Citing 0
Cited 13

Learning to Parse Pictures of People

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Stochastic Tracking of 3D Human Figures Using 2D Image Motion

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
A Framework for Robust Subspace Learning

International Journal of Computer Vision - Special Issue on Computational Vision at Brown University
Learning the Statistics of People in Images and Video

International Journal of Computer Vision - Special Issue on Computational Vision at Brown University
Modelling and estimating the pose of a human arm

Machine Vision and Applications - Special issue: Human modeling, analysis, and synthesis
Shape-From-Silhouette Across Time Part II: Applications to Human Modeling and Markerless Motion Tracking

International Journal of Computer Vision
Weighted and robust learning of subspace representations

Pattern Recognition
Human Pose Estimation Using Partial Configurations and Probabilistic Regions

International Journal of Computer Vision
Incremental and robust learning of subspace representations

Image and Vision Computing
Pose estimation and tracking using multivariate regression

Pattern Recognition Letters
Representing cyclic human motion using functional analysis

Image and Vision Computing
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion

International Journal of Computer Vision
Multivariate relevance vector machines for tracking

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a framework for constructing a linear subspace model of image appearance for complex articulated 3D figures such as humans and other animals. A commercial motion capture system provides 3D data that is aligned with images of subjects performing various activities. Portions of a limb's image appearance are seen from multiple views and for multiple subjects. From these partial views, weighted principal component analysis is used to construct a linear subspace representation of the "un-wrapped" image appearance of each limb. The linear sub-spaces provide a generative model of the object appearance that is exploited in a Bayesian particle filtering tracking sys-tem. Results of tracking single limbs and walking humans are presented.