A sequential Monte Carlo method for particle filters

Author

Gao, Hongzhi ; Green, Richard

Author_Institution

Dept. of Comput. Sci. & Software Eng., Univ. of Canterbury, Christchurch

fYear

2008

fDate

26-28 Nov. 2008

Firstpage

1

Lastpage

6

Abstract

An object oriented particle filter framework is proposed based on sequential Monte Carlo methods. Particle filter is an extensively used algorithm for vision based tracking systems. However, little work has been done in the past literature to investigate the implementation strategies of the particle filter algorithm. In this paper, we propose a framework based on open source particle filter libraries and evaluate respective advantages and disadvantages. The results support the proposed object oriented particle filter being a most useful tool for computer vision based stochastic prediction.

Keywords

Monte Carlo methods; computer vision; particle filtering (numerical methods); computer vision; particle filters; sequential Monte Carlo method; stochastic prediction; vision-based tracking systems; Application software; Computer science; Computer vision; Machine vision; Particle filters; Particle tracking; Software engineering; Software libraries; State-space methods; Stochastic processes; application framework; implementation strategy; particle filter;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Vision Computing New Zealand, 2008. IVCNZ 2008. 23rd International Conference

Conference_Location

Christchurch

Print_ISBN

978-1-4244-3780-1

Electronic_ISBN

978-1-4244-2583-9

Type

conf

DOI

10.1109/IVCNZ.2008.4762108

Filename

4762108