Forskning ved Københavns Universitet - Københavns Universitet

Forside

Data-driven importance distributions for articulated tracking

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Data-driven importance distributions for articulated tracking. / Hauberg, Søren; Pedersen, Kim Steenstrup.

Energy Minimization Methods in Computer Vision and Pattern Recognition: 8th International Conference, EMMCVPR 2011, St. Petersburg, Russia, July 25-27, 2011. Proceedings. red. / Yuri Boykov; Fredrik Kahl; Victor Lempitsky; Frank R. Schmidt. Springer, 2011. s. 287-299 (Lecture notes in computer science, Bind 6819).

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Hauberg, S & Pedersen, KS 2011, Data-driven importance distributions for articulated tracking. i Y Boykov, F Kahl, V Lempitsky & FR Schmidt (red), Energy Minimization Methods in Computer Vision and Pattern Recognition: 8th International Conference, EMMCVPR 2011, St. Petersburg, Russia, July 25-27, 2011. Proceedings. Springer, Lecture notes in computer science, bind 6819, s. 287-299, 8th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition, Sankt Petersborg, Rusland, 25/07/2011. https://doi.org/10.1007/978-3-642-23094-3_21

APA

Hauberg, S., & Pedersen, K. S. (2011). Data-driven importance distributions for articulated tracking. I Y. Boykov, F. Kahl, V. Lempitsky, & F. R. Schmidt (red.), Energy Minimization Methods in Computer Vision and Pattern Recognition: 8th International Conference, EMMCVPR 2011, St. Petersburg, Russia, July 25-27, 2011. Proceedings (s. 287-299). Springer. Lecture notes in computer science, Bind. 6819 https://doi.org/10.1007/978-3-642-23094-3_21

Vancouver

Hauberg S, Pedersen KS. Data-driven importance distributions for articulated tracking. I Boykov Y, Kahl F, Lempitsky V, Schmidt FR, red., Energy Minimization Methods in Computer Vision and Pattern Recognition: 8th International Conference, EMMCVPR 2011, St. Petersburg, Russia, July 25-27, 2011. Proceedings. Springer. 2011. s. 287-299. (Lecture notes in computer science, Bind 6819). https://doi.org/10.1007/978-3-642-23094-3_21

Author

Hauberg, Søren ; Pedersen, Kim Steenstrup. / Data-driven importance distributions for articulated tracking. Energy Minimization Methods in Computer Vision and Pattern Recognition: 8th International Conference, EMMCVPR 2011, St. Petersburg, Russia, July 25-27, 2011. Proceedings. red. / Yuri Boykov ; Fredrik Kahl ; Victor Lempitsky ; Frank R. Schmidt. Springer, 2011. s. 287-299 (Lecture notes in computer science, Bind 6819).

Bibtex

@inproceedings{34c263e44e8948409111c1d668c64428,
title = "Data-driven importance distributions for articulated tracking",
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.",
author = "S{\o}ren Hauberg and Pedersen, {Kim Steenstrup}",
year = "2011",
doi = "10.1007/978-3-642-23094-3_21",
language = "English",
isbn = "978-3-642-23093-6",
series = "Lecture notes in computer science",
publisher = "Springer",
pages = "287--299",
editor = "Yuri Boykov and Fredrik Kahl and Victor Lempitsky and Schmidt, {Frank R.}",
booktitle = "Energy Minimization Methods in Computer Vision and Pattern Recognition",
note = "null ; Conference date: 25-07-2011 Through 27-07-2011",

}

RIS

TY - GEN

T1 - Data-driven importance distributions for articulated tracking

AU - Hauberg, Søren

AU - Pedersen, Kim Steenstrup

N1 - Conference code: 8

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-642-23094-3_21

DO - 10.1007/978-3-642-23094-3_21

M3 - Article in proceedings

SN - 978-3-642-23093-6

T3 - Lecture notes in computer science

SP - 287

EP - 299

BT - Energy Minimization Methods in Computer Vision and Pattern Recognition

A2 - Boykov, Yuri

A2 - Kahl, Fredrik

A2 - Lempitsky, Victor

A2 - Schmidt, Frank R.

PB - Springer

Y2 - 25 July 2011 through 27 July 2011

ER -

ID: 170211892