Modeling self-occlusions in dynamic shape and appearance tracking

Handle URI:
http://hdl.handle.net/10754/564821
Title:
Modeling self-occlusions in dynamic shape and appearance tracking
Authors:
Yang, Yanchao; Sundaramoorthi, Ganesh ( 0000-0003-3471-6384 )
Abstract:
We present a method to track the precise shape of a dynamic object in video. Joint dynamic shape and appearance models, in which a template of the object is propagated to match the object shape and radiance in the next frame, are advantageous over methods employing global image statistics in cases of complex object radiance and cluttered background. In cases of complex 3D object motion and relative viewpoint change, self-occlusions and disocclusions of the object are prominent, and current methods employing joint shape and appearance models are unable to accurately 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. Experiments on video exhibiting occlusion/dis-occlusion, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy compared to recent methods employing joint shape/appearance models or employing global statistics. © 2013 IEEE.
KAUST Department:
Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Visual Computing Center (VCC)
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2013 IEEE International Conference on Computer Vision
Conference/Event name:
2013 14th IEEE International Conference on Computer Vision, ICCV 2013
Issue Date:
Dec-2013
DOI:
10.1109/ICCV.2013.32
Type:
Conference Paper
ISBN:
9781479928392
Appears in Collections:
Conference Papers; 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.accessioned2015-08-04T07:17:13Zen
dc.date.available2015-08-04T07:17:13Zen
dc.date.issued2013-12en
dc.identifier.isbn9781479928392en
dc.identifier.doi10.1109/ICCV.2013.32en
dc.identifier.urihttp://hdl.handle.net/10754/564821en
dc.description.abstractWe present a method to track the precise shape of a dynamic object in video. Joint dynamic shape and appearance models, in which a template of the object is propagated to match the object shape and radiance in the next frame, are advantageous over methods employing global image statistics in cases of complex object radiance and cluttered background. In cases of complex 3D object motion and relative viewpoint change, self-occlusions and disocclusions of the object are prominent, and current methods employing joint shape and appearance models are unable to accurately 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. Experiments on video exhibiting occlusion/dis-occlusion, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy compared to recent methods employing joint shape/appearance models or employing global statistics. © 2013 IEEE.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.subjectdis-occlusionsen
dc.subjectlevel set methodsen
dc.subjectobject trackingen
dc.subjectocclusionsen
dc.subjectoptical flowen
dc.subjectshape trackingen
dc.titleModeling self-occlusions in dynamic shape and appearance trackingen
dc.typeConference Paperen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journal2013 IEEE International Conference on Computer Visionen
dc.conference.date1 December 2013 through 8 December 2013en
dc.conference.name2013 14th IEEE International Conference on Computer Vision, ICCV 2013en
dc.conference.locationSydney, NSWen
kaust.authorYang, Yanchaoen
kaust.authorSundaramoorthi, Ganeshen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.