Adaptive Rao-Blackwellized particle filter and its evaluation for tracking in surveillance

Xinyu Xu, Baoxin Li

Research output: Contribution to journalArticle

72 Citations (Scopus)

Abstract

Particle filters can become quite inefficient when being applied to a high-dimensional state space since a prohibitively large number of samples may be required to approximate the underlying density functions with desired accuracy. In this paper, by proposing an adaptive Rao-Blackwellized particle filter for tracking in surveillance, we show how to exploit the analytical relationship among state variables to improve the efficiency and accuracy of a regular particle filter. Essentially, the distributions of the linear variables are updated analytically using a Kalman filter which is associated with each particle in a particle filtering framework. Experiments and detailed performance analysis using both simulated data and real video sequences reveal that the proposed method results in more accurate tracking than a regular particle filter.

Original languageEnglish (US)
Pages (from-to)838-849
Number of pages12
JournalIEEE Transactions on Image Processing
Volume16
Issue number3
DOIs
StatePublished - Mar 2007

Fingerprint

Particle Filter
Kalman filters
Surveillance
Probability density function
Evaluation
Experiments
Particle Filtering
Density Function
Kalman Filter
Performance Analysis
State Space
High-dimensional
Experiment

Keywords

  • Particle filter
  • Rao-Blackwellization
  • Video-based surveillance
  • Visual tracking

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Graphics and Computer-Aided Design
  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition

Cite this

Adaptive Rao-Blackwellized particle filter and its evaluation for tracking in surveillance. / Xu, Xinyu; Li, Baoxin.

In: IEEE Transactions on Image Processing, Vol. 16, No. 3, 03.2007, p. 838-849.

Research output: Contribution to journalArticle

@article{0c3fd49edf0c4321815289f4c606b2ad,
title = "Adaptive Rao-Blackwellized particle filter and its evaluation for tracking in surveillance",
abstract = "Particle filters can become quite inefficient when being applied to a high-dimensional state space since a prohibitively large number of samples may be required to approximate the underlying density functions with desired accuracy. In this paper, by proposing an adaptive Rao-Blackwellized particle filter for tracking in surveillance, we show how to exploit the analytical relationship among state variables to improve the efficiency and accuracy of a regular particle filter. Essentially, the distributions of the linear variables are updated analytically using a Kalman filter which is associated with each particle in a particle filtering framework. Experiments and detailed performance analysis using both simulated data and real video sequences reveal that the proposed method results in more accurate tracking than a regular particle filter.",
keywords = "Particle filter, Rao-Blackwellization, Video-based surveillance, Visual tracking",
author = "Xinyu Xu and Baoxin Li",
year = "2007",
month = "3",
doi = "10.1109/TIP.2007.891074",
language = "English (US)",
volume = "16",
pages = "838--849",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Adaptive Rao-Blackwellized particle filter and its evaluation for tracking in surveillance

AU - Xu, Xinyu

AU - Li, Baoxin

PY - 2007/3

Y1 - 2007/3

N2 - Particle filters can become quite inefficient when being applied to a high-dimensional state space since a prohibitively large number of samples may be required to approximate the underlying density functions with desired accuracy. In this paper, by proposing an adaptive Rao-Blackwellized particle filter for tracking in surveillance, we show how to exploit the analytical relationship among state variables to improve the efficiency and accuracy of a regular particle filter. Essentially, the distributions of the linear variables are updated analytically using a Kalman filter which is associated with each particle in a particle filtering framework. Experiments and detailed performance analysis using both simulated data and real video sequences reveal that the proposed method results in more accurate tracking than a regular particle filter.

AB - Particle filters can become quite inefficient when being applied to a high-dimensional state space since a prohibitively large number of samples may be required to approximate the underlying density functions with desired accuracy. In this paper, by proposing an adaptive Rao-Blackwellized particle filter for tracking in surveillance, we show how to exploit the analytical relationship among state variables to improve the efficiency and accuracy of a regular particle filter. Essentially, the distributions of the linear variables are updated analytically using a Kalman filter which is associated with each particle in a particle filtering framework. Experiments and detailed performance analysis using both simulated data and real video sequences reveal that the proposed method results in more accurate tracking than a regular particle filter.

KW - Particle filter

KW - Rao-Blackwellization

KW - Video-based surveillance

KW - Visual tracking

UR - http://www.scopus.com/inward/record.url?scp=33947248999&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947248999&partnerID=8YFLogxK

U2 - 10.1109/TIP.2007.891074

DO - 10.1109/TIP.2007.891074

M3 - Article

C2 - 17357741

AN - SCOPUS:33947248999

VL - 16

SP - 838

EP - 849

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 3

ER -