Visual tracking of multiple targets by Multi-Bernoulli filtering of background subtracted image data

Most visual multi-target tracking techniques in the literature employ a detection routine to map the image data to point measurements that are usually further processed by a filter. In this paper, we present a visual tracking technique based on a multi-target filtering algorithm that operates direct...

Full description

Bibliographic Details
Main Authors: Hoseinnezhad, R., Vo, Ba-Ngu, Vu, T.N.
Other Authors: Ying Tan
Format: Book Chapter
Published: Springer 2011
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/45604
_version_ 1848757332655210496
author Hoseinnezhad, R.
Vo, Ba-Ngu
Vu, T.N.
author2 Ying Tan
author_facet Ying Tan
Hoseinnezhad, R.
Vo, Ba-Ngu
Vu, T.N.
author_sort Hoseinnezhad, R.
building Curtin Institutional Repository
collection Online Access
description Most visual multi-target tracking techniques in the literature employ a detection routine to map the image data to point measurements that are usually further processed by a filter. In this paper, we present a visual tracking technique based on a multi-target filtering algorithm that operates directly on the image observations and does not require any detection nor training patterns. Instead, we use the recent history of image data for non-parametric background subtraction and apply an efficient multi-target filtering technique, known as the multi-Bernoulli filter, on the resulting grey scale image data. In our experiments, we applied our method to track multiple people in three video sequences from the CAVIAR dataset. The results show that our method can automatically track multiple interacting targets and quickly finds targets entering or leaving the scene.
first_indexed 2025-11-14T09:26:25Z
format Book Chapter
id curtin-20.500.11937-45604
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:26:25Z
publishDate 2011
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-456042023-02-02T07:57:34Z Visual tracking of multiple targets by Multi-Bernoulli filtering of background subtracted image data Hoseinnezhad, R. Vo, Ba-Ngu Vu, T.N. Ying Tan Yuhui Shi Yi Chai Guoyin Wang multi-Bernoulli multi-target tracking Bayesian estimation random finite sets visual tracking Most visual multi-target tracking techniques in the literature employ a detection routine to map the image data to point measurements that are usually further processed by a filter. In this paper, we present a visual tracking technique based on a multi-target filtering algorithm that operates directly on the image observations and does not require any detection nor training patterns. Instead, we use the recent history of image data for non-parametric background subtraction and apply an efficient multi-target filtering technique, known as the multi-Bernoulli filter, on the resulting grey scale image data. In our experiments, we applied our method to track multiple people in three video sequences from the CAVIAR dataset. The results show that our method can automatically track multiple interacting targets and quickly finds targets entering or leaving the scene. 2011 Book Chapter http://hdl.handle.net/20.500.11937/45604 10.1007/978-3-642-21524-7_63 Springer restricted
spellingShingle multi-Bernoulli
multi-target tracking
Bayesian estimation
random finite sets
visual tracking
Hoseinnezhad, R.
Vo, Ba-Ngu
Vu, T.N.
Visual tracking of multiple targets by Multi-Bernoulli filtering of background subtracted image data
title Visual tracking of multiple targets by Multi-Bernoulli filtering of background subtracted image data
title_full Visual tracking of multiple targets by Multi-Bernoulli filtering of background subtracted image data
title_fullStr Visual tracking of multiple targets by Multi-Bernoulli filtering of background subtracted image data
title_full_unstemmed Visual tracking of multiple targets by Multi-Bernoulli filtering of background subtracted image data
title_short Visual tracking of multiple targets by Multi-Bernoulli filtering of background subtracted image data
title_sort visual tracking of multiple targets by multi-bernoulli filtering of background subtracted image data
topic multi-Bernoulli
multi-target tracking
Bayesian estimation
random finite sets
visual tracking
url http://hdl.handle.net/20.500.11937/45604