Gaussian-like spatial priors for articulated tracking

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

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.
OriginalsprogEngelsk
TitelComputer Vision - ECCV 2010 : 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I
RedaktørerKostas Daniilidis, Petros Maragos, Nikos Paragios
Antal sider13
Vol/bindPart I
ForlagSpringer
Publikationsdato2010
Sider425-437
ISBN (Trykt)978-3-642-15548-2
ISBN (Elektronisk)978-3-642-15549-9
DOI
StatusUdgivet - 2010
Begivenhed11th European Conference on Computer Vision - Heraklion, Grækenland
Varighed: 5 sep. 201011 sep. 2010
Konferencens nummer: 11

Konference

Konference11th European Conference on Computer Vision
Nummer11
LandGrækenland
ByHeraklion
Periode05/09/201011/09/2010
NavnLecture notes in computer science
Nummer6311
ISSN0302-9743

ID: 20921496