Non-overlapping Distributed Tracking System Utilizing Particle Filter

Tracking people across multiple cameras is a challenging research area in visual computing, especially when these cameras have non-overlapping field of views. The important task is to associate a current subject with other prior appearances of the same subject across time and space in a camera netwo...

Full description

Bibliographic Details
Main Authors: Lim, Fee Lee, Leoputra, Wilson, Tan, Tele
Format: Journal Article
Published: Springer Netherlands 2007
Online Access:http://hdl.handle.net/20.500.11937/41093
_version_ 1848756048621469696
author Lim, Fee Lee
Leoputra, Wilson
Tan, Tele
author_facet Lim, Fee Lee
Leoputra, Wilson
Tan, Tele
author_sort Lim, Fee Lee
building Curtin Institutional Repository
collection Online Access
description Tracking people across multiple cameras is a challenging research area in visual computing, especially when these cameras have non-overlapping field of views. The important task is to associate a current subject with other prior appearances of the same subject across time and space in a camera network. Several known techniques rely on Bayesian approaches to perform the matching task. However, these approaches do not scale well when the dimension of the problem increases; e.g. when the number of subject or possible path increases. The aim of this paper is to propose a unified tracking framework using particle filters to efficiently switch between visual tracking (field of view tracking) and track prediction (non-overlapping region tracking). The particle filter tracking system utilizes a map (known environment) to assist the tracking process when targets leave the field of view of any camera. We implemented and tested this tracking approach in an in-house multiple cameras system as well as using on-line data. Promising results were obtained which suggested the feasibility of such an approach.
first_indexed 2025-11-14T09:06:00Z
format Journal Article
id curtin-20.500.11937-41093
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:06:00Z
publishDate 2007
publisher Springer Netherlands
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-410932017-09-13T14:28:47Z Non-overlapping Distributed Tracking System Utilizing Particle Filter Lim, Fee Lee Leoputra, Wilson Tan, Tele Tracking people across multiple cameras is a challenging research area in visual computing, especially when these cameras have non-overlapping field of views. The important task is to associate a current subject with other prior appearances of the same subject across time and space in a camera network. Several known techniques rely on Bayesian approaches to perform the matching task. However, these approaches do not scale well when the dimension of the problem increases; e.g. when the number of subject or possible path increases. The aim of this paper is to propose a unified tracking framework using particle filters to efficiently switch between visual tracking (field of view tracking) and track prediction (non-overlapping region tracking). The particle filter tracking system utilizes a map (known environment) to assist the tracking process when targets leave the field of view of any camera. We implemented and tested this tracking approach in an in-house multiple cameras system as well as using on-line data. Promising results were obtained which suggested the feasibility of such an approach. 2007 Journal Article http://hdl.handle.net/20.500.11937/41093 10.1007/s11265-007-0091-4 Springer Netherlands fulltext
spellingShingle Lim, Fee Lee
Leoputra, Wilson
Tan, Tele
Non-overlapping Distributed Tracking System Utilizing Particle Filter
title Non-overlapping Distributed Tracking System Utilizing Particle Filter
title_full Non-overlapping Distributed Tracking System Utilizing Particle Filter
title_fullStr Non-overlapping Distributed Tracking System Utilizing Particle Filter
title_full_unstemmed Non-overlapping Distributed Tracking System Utilizing Particle Filter
title_short Non-overlapping Distributed Tracking System Utilizing Particle Filter
title_sort non-overlapping distributed tracking system utilizing particle filter
url http://hdl.handle.net/20.500.11937/41093