Non-Rigid Structure from Motion using non-Parametric Tracking and Non-Linear Optimization

Authors:
Alessio Del Bue;Fabrizio Smeraldi;Lourdes Agapito
Affiliations:
Queen Mary, University of London, UK;Queen Mary, University of London, UK;Queen Mary, University of London, UK
Venue:
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 1 - Volume 01
Year:
2004

Citing 0
Cited 8

Non-Rigid Stereo Factorization

International Journal of Computer Vision
Structure and motion of nonrigid object under perspective projection

Pattern Recognition Letters
Recursive Shape and Pose Determination Using Deformable Model

CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
Head Pose Determination Using Synthetic Images

ACIVS '08 Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems
Quasi-perspective Projection Model: Theory and Application to Structure and Motion Factorization from Uncalibrated Image Sequences

International Journal of Computer Vision
Learning a generic 3D face model from 2D image databases using incremental Structure-from-Motion

Image and Vision Computing
Non-rigid face modelling using shape priors

AMFG'05 Proceedings of the Second international conference on Analysis and Modelling of Faces and Gestures
Real-time modeling of face deformation for 3d head pose estimation

AMFG'05 Proceedings of the Second international conference on Analysis and Modelling of Faces and Gestures

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we address the problem of estimating the 3D structure and motion of a deformable non-rigid object from a sequence of uncalibrated images. It has been recently shown that if the deformation is modelled as a linear combination of basis shapes both the motion and the 3D structure of the object may be recovered using an extension of Tomasi and Kanade's factorization algorithm for affine cameras. The main drawback of the existing methods is that the non-rigid factorization algorithm does not provide a correct estimate of the motion: the motion matrix has a repetitive structure which is not respected by the factorization algorithm. This also affects the estimation of the 3D shape. In this paper we present a non-linear optimization method which minimizes image reprojection error and imposes the correct structure onto the motion matrix by choosing an appropriate parameterization. In addition, we propose a novel non-rigid tracking algorithm based on the use of ranklets, a multiscale family of rank features. Finally, we show that improved motion and shape estimates are obtained on a real image sequence of a person's face which is moving and changing expression.