Skip navigation
Skip navigation

Convex Optimization for Deformable Surface 3-D Tracking

Salzmann, Mathieu; Hartley, Richard; Fua, Pascal

Description

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...[Show more]

dc.contributor.authorSalzmann, Mathieu
dc.contributor.authorHartley, Richard
dc.contributor.authorFua, Pascal
dc.contributor.editorA. Elgammal et al.
dc.coverage.spatialRio de Janeiro Brazil
dc.date.accessioned2015-12-08T22:16:29Z
dc.date.createdOctober 14-20 2007
dc.identifier.urihttp://hdl.handle.net/1885/30700
dc.description.abstract3-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.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)
dc.relation.ispartofseriesIEEE International Conference on Computer Vision (ICCV 2007)
dc.sourceProceedings of ICCV 2007
dc.subjectKeywords: Artificial intelligence; Computer networks; Computer vision; Deformation; Image processing; Optimization; Photography; Shape optimization; Surface chemistry; Three dimensional; Two dimensional; Video recording; International conferences; Smoothness constr
dc.titleConvex Optimization for Deformable Surface 3-D Tracking
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2007
local.identifier.absfor080104 - Computer Vision
local.identifier.ariespublicationu4334215xPUB76
local.type.statusPublished Version
local.contributor.affiliationSalzmann, Mathieu, Ecole Polytechnique Federale de Lausanne
local.contributor.affiliationHartley, Richard, College of Engineering and Computer Science, ANU
local.contributor.affiliationFua, Pascal, Ecole Polytechnique Federale de Lausanne
local.description.embargo2037-12-31
local.bibliographicCitation.startpage8
local.identifier.doi10.1109/ICCV.2007.4409031
dc.date.updated2015-12-08T08:01:40Z
local.identifier.scopusID2-s2.0-50649105297
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Salzmann_Convex_Optimization_for_2007.pdf4.61 MBAdobe PDF    Request a copy


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

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator