Forskning ved Københavns Universitet - Københavns Universitet

Forside

Data-driven importance distributions for articulated tracking

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

We present two data-driven importance distributions for particle filterbased
articulated tracking; one based on background subtraction, another on depth
information. In order to keep the algorithms efficient, we represent human poses
in terms of spatial joint positions. To ensure constant bone lengths, the joint
positions are confined to a non-linear representation manifold embedded in a
high-dimensional Euclidean space. We define the importance distributions in the
embedding space and project them onto the representation manifold. The resulting
importance distributions are used in a particle filter, where they improve both
accuracy and efficiency of the tracker. In fact, they triple the effective number of
samples compared to the most commonly used importance distribution at little
extra computational cost.
OriginalsprogEngelsk
TitelEnergy Minimization Methods in Computer Vision and Pattern Recognition : 8th International Conference, EMMCVPR 2011, St. Petersburg, Russia, July 25-27, 2011. Proceedings
RedaktørerYuri Boykov, Fredrik Kahl, Victor Lempitsky, Frank R. Schmidt
Antal sider13
ForlagSpringer
Publikationsdato2011
Sider287-299
ISBN (Trykt)978-3-642-23093-6
ISBN (Elektronisk)978-3-642-23094-3
DOI
StatusUdgivet - 2011
Begivenhed8th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition - Sankt Petersborg, Rusland
Varighed: 25 jul. 201127 jul. 2011
Konferencens nummer: 8

Konference

Konference8th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Nummer8
LandRusland
BySankt Petersborg
Periode25/07/201127/07/2011
NavnLecture notes in computer science
Vol/bind6819
ISSN0302-9743

ID: 170211892