Efficient mean shift belief propagation for vision tracking

Research output: Chapter in Book/Report/Conference proceedingConference contribution

30 Citations (Scopus)

Abstract

A mechanism for efficient mean-shift belief propagation (MSBP) is introduced. The novelty of our work is to use mean-shift to perform nonparametric mode-seeking on belief surfaces generated within the belief propagation framework. Belief Propagation (BP) is a powerful solution for performing inference in graphical models. However, there is a quadratic increase in the cost of computation with respect to the size of the hidden variable space. While the recently proposed nonparametric belief propagation (NBP) has better performance in terms of speed, even for continuous hidden variable spaces, computation is still slow due to the particle filter sampling process. Our MSBP method only needs to compute a local grid of samples of the belief surface during each iteration. This approach needs a significantly smaller number of samples than NBP, reducing computation time, yet it also yields more accurate and stable solutions. The efficiency and robustness of MSBP is compared against other variants of BP on applications in multi-target tracking and 2D articulated body tracking.

Original languageEnglish (US)
Title of host publication26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
DOIs
StatePublished - Sep 23 2008
Event26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR - Anchorage, AK, United States
Duration: Jun 23 2008Jun 28 2008

Publication series

Name26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

Other

Other26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
CountryUnited States
CityAnchorage, AK
Period6/23/086/28/08

Fingerprint

Target tracking
Sampling
Costs

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering

Cite this

Park, M., Liu, Y., & Collins, R. (2008). Efficient mean shift belief propagation for vision tracking. In 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR [4587508] (26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR). https://doi.org/10.1109/CVPR.2008.4587508
Park, Minwoo ; Liu, Yanxi ; Collins, Robert. / Efficient mean shift belief propagation for vision tracking. 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2008. (26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR).
@inproceedings{9e96dd448b2f43a499aebdb473ddca59,
title = "Efficient mean shift belief propagation for vision tracking",
abstract = "A mechanism for efficient mean-shift belief propagation (MSBP) is introduced. The novelty of our work is to use mean-shift to perform nonparametric mode-seeking on belief surfaces generated within the belief propagation framework. Belief Propagation (BP) is a powerful solution for performing inference in graphical models. However, there is a quadratic increase in the cost of computation with respect to the size of the hidden variable space. While the recently proposed nonparametric belief propagation (NBP) has better performance in terms of speed, even for continuous hidden variable spaces, computation is still slow due to the particle filter sampling process. Our MSBP method only needs to compute a local grid of samples of the belief surface during each iteration. This approach needs a significantly smaller number of samples than NBP, reducing computation time, yet it also yields more accurate and stable solutions. The efficiency and robustness of MSBP is compared against other variants of BP on applications in multi-target tracking and 2D articulated body tracking.",
author = "Minwoo Park and Yanxi Liu and Robert Collins",
year = "2008",
month = "9",
day = "23",
doi = "10.1109/CVPR.2008.4587508",
language = "English (US)",
isbn = "9781424422432",
series = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR",
booktitle = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR",

}

Park, M, Liu, Y & Collins, R 2008, Efficient mean shift belief propagation for vision tracking. in 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR., 4587508, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Anchorage, AK, United States, 6/23/08. https://doi.org/10.1109/CVPR.2008.4587508

Efficient mean shift belief propagation for vision tracking. / Park, Minwoo; Liu, Yanxi; Collins, Robert.

26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2008. 4587508 (26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Efficient mean shift belief propagation for vision tracking

AU - Park, Minwoo

AU - Liu, Yanxi

AU - Collins, Robert

PY - 2008/9/23

Y1 - 2008/9/23

N2 - A mechanism for efficient mean-shift belief propagation (MSBP) is introduced. The novelty of our work is to use mean-shift to perform nonparametric mode-seeking on belief surfaces generated within the belief propagation framework. Belief Propagation (BP) is a powerful solution for performing inference in graphical models. However, there is a quadratic increase in the cost of computation with respect to the size of the hidden variable space. While the recently proposed nonparametric belief propagation (NBP) has better performance in terms of speed, even for continuous hidden variable spaces, computation is still slow due to the particle filter sampling process. Our MSBP method only needs to compute a local grid of samples of the belief surface during each iteration. This approach needs a significantly smaller number of samples than NBP, reducing computation time, yet it also yields more accurate and stable solutions. The efficiency and robustness of MSBP is compared against other variants of BP on applications in multi-target tracking and 2D articulated body tracking.

AB - A mechanism for efficient mean-shift belief propagation (MSBP) is introduced. The novelty of our work is to use mean-shift to perform nonparametric mode-seeking on belief surfaces generated within the belief propagation framework. Belief Propagation (BP) is a powerful solution for performing inference in graphical models. However, there is a quadratic increase in the cost of computation with respect to the size of the hidden variable space. While the recently proposed nonparametric belief propagation (NBP) has better performance in terms of speed, even for continuous hidden variable spaces, computation is still slow due to the particle filter sampling process. Our MSBP method only needs to compute a local grid of samples of the belief surface during each iteration. This approach needs a significantly smaller number of samples than NBP, reducing computation time, yet it also yields more accurate and stable solutions. The efficiency and robustness of MSBP is compared against other variants of BP on applications in multi-target tracking and 2D articulated body tracking.

UR - http://www.scopus.com/inward/record.url?scp=51949103187&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51949103187&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2008.4587508

DO - 10.1109/CVPR.2008.4587508

M3 - Conference contribution

SN - 9781424422432

T3 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

BT - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

ER -

Park M, Liu Y, Collins R. Efficient mean shift belief propagation for vision tracking. In 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2008. 4587508. (26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR). https://doi.org/10.1109/CVPR.2008.4587508