Shape tracking with occlusions via coarse-to-fine region-based sobolev descent

Handle URI:
http://hdl.handle.net/10754/564169
Title:
Shape tracking with occlusions via coarse-to-fine region-based sobolev descent
Authors:
Yang, Yanchao; Sundaramoorthi, Ganesh ( 0000-0003-3471-6384 )
Abstract:
We present a method to track the shape of an object from video. The method uses a joint shape and appearance model of the object, which is propagated to match shape and radiance in subsequent frames, determining object shape. Self-occlusions and dis-occlusions of the object from camera and object motion pose difficulties to joint shape and appearance models in tracking. They are unable to adapt to new shape and appearance information, leading to inaccurate shape detection. In this work, we model self-occlusions and dis-occlusions in a joint shape and appearance tracking framework. Self-occlusions and the warp to propagate the model are coupled, thus we formulate a joint optimization problem. We derive a coarse-to-fine optimization method, advantageous in tracking, that initially perturbs the model by coarse perturbations before transitioning to finer-scale perturbations seamlessly. This coarse-to-fine behavior is automatically induced by gradient descent on a novel infinite-dimensional Riemannian manifold that we introduce. The manifold consists of planar parameterized regions, and the metric that we introduce is a novel Sobolev metric. Experiments on video exhibiting occlusions/dis-occlusions, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy. © 2014 IEEE.
KAUST Department:
Electrical Engineering Program; Applied Mathematics and Computational Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Visual Computing Center (VCC)
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Issue Date:
1-May-2015
DOI:
10.1109/TPAMI.2014.2360380
ARXIV:
arXiv:1208.4391
Type:
Article
ISSN:
01628828
Sponsors:
This work was funded by KAUST Baseline and Visual Computing Center funding.
Additional Links:
http://arxiv.org/abs/arXiv:1208.4391v2
Appears in Collections:
Articles; Applied Mathematics and Computational Science Program; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorYang, Yanchaoen
dc.contributor.authorSundaramoorthi, Ganeshen
dc.date.accessioned2015-08-03T12:34:54Zen
dc.date.available2015-08-03T12:34:54Zen
dc.date.issued2015-05-01en
dc.identifier.issn01628828en
dc.identifier.doi10.1109/TPAMI.2014.2360380en
dc.identifier.urihttp://hdl.handle.net/10754/564169en
dc.description.abstractWe present a method to track the shape of an object from video. The method uses a joint shape and appearance model of the object, which is propagated to match shape and radiance in subsequent frames, determining object shape. Self-occlusions and dis-occlusions of the object from camera and object motion pose difficulties to joint shape and appearance models in tracking. They are unable to adapt to new shape and appearance information, leading to inaccurate shape detection. In this work, we model self-occlusions and dis-occlusions in a joint shape and appearance tracking framework. Self-occlusions and the warp to propagate the model are coupled, thus we formulate a joint optimization problem. We derive a coarse-to-fine optimization method, advantageous in tracking, that initially perturbs the model by coarse perturbations before transitioning to finer-scale perturbations seamlessly. This coarse-to-fine behavior is automatically induced by gradient descent on a novel infinite-dimensional Riemannian manifold that we introduce. The manifold consists of planar parameterized regions, and the metric that we introduce is a novel Sobolev metric. Experiments on video exhibiting occlusions/dis-occlusions, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy. © 2014 IEEE.en
dc.description.sponsorshipThis work was funded by KAUST Baseline and Visual Computing Center funding.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://arxiv.org/abs/arXiv:1208.4391v2en
dc.subjectdeformable templatesen
dc.subjectObject segmentation from videoen
dc.subjectobject trackingen
dc.subjectocclusionsen
dc.subjectoptical flowen
dc.subjectshape metricsen
dc.titleShape tracking with occlusions via coarse-to-fine region-based sobolev descenten
dc.typeArticleen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentApplied Mathematics and Computational Science Programen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journalIEEE Transactions on Pattern Analysis and Machine Intelligenceen
dc.identifier.arxividarXiv:1208.4391en
kaust.authorYang, Yanchaoen
kaust.authorSundaramoorthi, Ganeshen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.