Authors: Del Bue, Alessio
Stošić, Marko 
Dodig, Marija 
Xavier, João
Title: 2D-3D registration of deformable shapes with manifold projection
Journal: Proceedings - International Conference on Image Processing, ICIP
First page: 1061
Last page: 1064
Conference: IEEE International Conference on Image Processing, ICIP 2009; Cairo; Egypt; 7 November 2009 through 10 November 2009
Issue Date: 1-Jan-2009
ISBN: 978-1-424-45654-3
ISSN: 1522-4880
DOI: 10.1109/ICIP.2009.5413705
We present an algorithm able to register a known 3D deformable model to a set of 2D matched points extracted from a single image. Unlike previous approaches, the problem is solved simultaneously for both the rigid and non-rigid parameters of the model. The key advantage of our approach is the projection of an initial affine estimation of the motion parameters into the motion manifold corresponding to the exact parametrization of the problem. This projection is formulated as theminimization of the distance between the affine solution and the surface of the manifold. Such optimization results in a quadratically constrained quadratic minimization problem that can be efficiently solved with standard optimization tools. Synthetic and real tests demonstrate the effectiveness of the approach.
Keywords: Deformable modelling | Image registration | Manifold projection | Quadratic optimization
Publisher: IEEE

Show full item record


checked on Jun 20, 2024

Page view(s)

checked on May 9, 2024

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.