Stick it! Articulated tracking using spatial rigid object priors

Søren Hauberg, Kim Steenstrup Pedersen

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

9 Citationer (Scopus)

Abstract

Articulated tracking of humans is a well-studied field, but most work has
treated the humans as being independent of the environment. Recently,
Kjellstrom et al. showed how knowledge of interaction with
a known rigid object provides constraints that lower the degrees of freedom in
the model. While the phrased problem is interesting, the resulting algorithm
is computationally too demanding to be of practical use. We present a simple
and elegant model for describing this problem. The resulting algorithm is
computationally much more efficient, while it at the same time produces
superior results.
OriginalsprogEngelsk
TitelComputer Vision – ACCV 2010 : 10th Asian Conference on Computer Vision, Queenstown, New Zealand, November 8-12, 2010, Revised Selected Papers, Part III
RedaktørerRon Kimmel, Reinhard Klette, Akihiro Sugimoto
Antal sider12
Vol/bindIII
ForlagSpringer
Publikationsdato2011
Sider758-769
ISBN (Trykt)978-3-642-19317-0
ISBN (Elektronisk)978-3-642-19318-7
DOI
StatusUdgivet - 2011
Begivenhed10th Asian Conference on Computer Vision - Queenstown, New Zealand
Varighed: 8 nov. 201012 nov. 2010
Konferencens nummer: 10

Konference

Konference10th Asian Conference on Computer Vision
Nummer10
Land/OmrådeNew Zealand
ByQueenstown
Periode08/11/201012/11/2010
NavnLecture notes in computer science
Vol/bind6494
ISSN0302-9743

Bibliografisk note

Video material available at: http://image.diku.dk/HUMIM/accv2010/

Citationsformater