Gaussian-like spatial priors for articulated tracking

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

We present an analysis of the spatial covariance structure of an articulated
motion prior in which joint angles have a known covariance structure. From this,
a well-known, but often ignored, deficiency of the kinematic skeleton representation becomes clear: spatial variance not only depends on limb lengths,
but also increases as the kinematic chains are traversed. We then present two     similar Gaussian-like motion priors that are explicitly expressed spatially     and as such avoids any variance coming from the representation. The resulting priors are both simple and easy to implement, yet they provide superior predictions.
Original languageEnglish
Title of host publicationComputer Vision - ECCV 2010 : 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I
EditorsKostas Daniilidis, Petros Maragos, Nikos Paragios
Number of pages13
VolumePart I
PublisherSpringer
Publication date2010
Pages425-437
ISBN (Print)978-3-642-15548-2
ISBN (Electronic)978-3-642-15549-9
DOIs
Publication statusPublished - 2010
Event11th European Conference on Computer Vision - Heraklion, Greece
Duration: 5 Sep 201011 Sep 2010
Conference number: 11

Conference

Conference11th European Conference on Computer Vision
Nummer11
LandGreece
ByHeraklion
Periode05/09/201011/09/2010
SeriesLecture notes in computer science
Number6311
ISSN0302-9743

ID: 20921496