Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/20275

Title: Behaviour based particle filtering for human articulated motion tracking
Authors: Darby, John
Li, Baihua
Costen, Nicholas
Issue Date: 2008
Publisher: © IEEE
Citation: DARBY, J., LI, B. and COSTEN, N., 2008. Behaviour based particle filtering for human articulated motion tracking. 19th International Conference on Pattern Recognition (ICPR 2008), Tampa, FL, 8th-11th December 2008, pp.3125 -3128
Abstract: This paper presents an approach to human motion tracking using multiple pre-trained activity models for propagation of particles in Annealed Particle Filtering. Hidden Markov models are trained on dimensionally reduced joint angle data to produce models of activity. Particles are divided between models for propagation by HMM synthesis, before converging on a solution during the annealing process. The approach facilitates multi-view tracking of unknown subjects performing multiple known activities with low particle numbers.
Description: This is the accepted manuscript version of the paper. © 2008 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Version: Accepted for publication
DOI: 10.1109/ICPR.2008.4761157
URI: https://dspace.lboro.ac.uk/2134/20275
Publisher Link: http://dx.doi.org/10.1109/ICPR.2008.4761157
ISBN: 9781424421749
ISSN: 1051-4651
Appears in Collections:Conference Papers and Presentations (Computer Science)

Files associated with this item:

File Description SizeFormat
ICPR08-HMM_APF_stereoImage.pdfAccepted version975.61 kBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.