Abstract
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.
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.
Originalsprog | Engelsk |
---|---|
Titel | Energy Minimization Methods in Computer Vision and Pattern Recognition : 8th International Conference, EMMCVPR 2011, St. Petersburg, Russia, July 25-27, 2011. Proceedings |
Redaktører | Yuri Boykov, Fredrik Kahl, Victor Lempitsky, Frank R. Schmidt |
Antal sider | 13 |
Forlag | Springer |
Publikationsdato | 2011 |
Sider | 287-299 |
ISBN (Trykt) | 978-3-642-23093-6 |
ISBN (Elektronisk) | 978-3-642-23094-3 |
DOI | |
Status | Udgivet - 2011 |
Begivenhed | 8th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition - Sankt Petersborg, Rusland Varighed: 25 jul. 2011 → 27 jul. 2011 Konferencens nummer: 8 |
Konference
Konference | 8th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition |
---|---|
Nummer | 8 |
Land/Område | Rusland |
By | Sankt Petersborg |
Periode | 25/07/2011 → 27/07/2011 |
Navn | Lecture notes in computer science |
---|---|
Vol/bind | 6819 |
ISSN | 0302-9743 |