Convex Optimization for Deformable Surface 3-D Tracking
Date
2007
Authors
Salzmann, Mathieu
Hartley, Richard
Fua, Pascal
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers (IEEE Inc)
Abstract
3-D shape recovery of non-rigid surfaces from 3-D to 2-D correspondences is an under-constrained problem that requires prior knowledge of the possible deformations. State-of-the-art solutions involve enforcing smoothness constraints that limit their applicability and prevent the recovery of sharply folding and creasing surfaces. Here, we propose a method that does not require such smoothness constraints. Instead, we represent surfaces as triangulated meshes and, assuming the pose in the first frame to be known, disallow large changes of edge orientation between consecutive frames, which is a generally applicable constraint when tracking surfaces in a 25 frames-per-second video sequence. We will show that tracking under these constraints can be formulated as a Second Order Cone Programming feasibility problem. This yields a convex optimization problem with stable solutions for a wide range of surfaces with very different physical properties.
Description
Keywords
Artificial intelligence, Computer networks, Computer vision, Deformation, Image processing, Optimization, Photography, Shape optimization, Surface chemistry, Three dimensional, Two dimensional, Video recording, International conferences
Citation
Collections
Source
Proceedings of ICCV 2007
Type
Conference paper
Book Title
Entity type
Access Statement
License Rights
Restricted until
2037-12-31
Downloads
File
Description