Gravity optimised particle filter for hand tracking

Gravity optimised particle filter for hand tracking

This paper presents a gravity optimised particle filter (GOPF) where the magnitude of the gravitational force for every particle is proportional to its weight. GOPF attracts nearby particles and replicates new particles as if moving the particles towards the peak of the likelihood distribution, impr...

Full description

Bibliographic Details
Main Authors: Morshidi, Malik Arman, Tjahjadi, Tardi
Format: Article
Language:English
Published: Elsevier 2014
Subjects:
Q300 Cybernetics
T Technology (General)
Online Access:http://irep.iium.edu.my/35420/
http://irep.iium.edu.my/35420/
http://irep.iium.edu.my/35420/
http://irep.iium.edu.my/35420/1/Gravity_Optimised_Particle_Filter_for_Hand_Tracking.pdf
id iium-35420
recordtype eprints
spelling iium-354202018-06-25T00:27:33Z http://irep.iium.edu.my/35420/ Gravity optimised particle filter for hand tracking Morshidi, Malik Arman Tjahjadi, Tardi Q300 Cybernetics T Technology (General) This paper presents a gravity optimised particle filter (GOPF) where the magnitude of the gravitational force for every particle is proportional to its weight. GOPF attracts nearby particles and replicates new particles as if moving the particles towards the peak of the likelihood distribution, improving the sampling efficiency. GOPF is incorporated into a technique for hand features tracking. A fast approach to hand features detection and labelling using convexity defects is also presented. Experimental results show that GOPF outperforms the standard particle filter and its variants, as well as state-of-the-art CamShift guided particle filter using a significantly reduced number of particles. Elsevier 2014-01 Article PeerReviewed application/pdf en http://irep.iium.edu.my/35420/1/Gravity_Optimised_Particle_Filter_for_Hand_Tracking.pdf Morshidi, Malik Arman and Tjahjadi, Tardi (2014) Gravity optimised particle filter for hand tracking. Pattern Recognition Letters, 47 (1). pp. 194-207. ISSN 01678655 http://dx.doi.org/10.1016/j.patcog.2013.06.032 doi:10.1016/j.patcog.2013.06.032
repository_type Digital Repository
institution_category Local University
institution International Islamic University Malaysia
building IIUM Repository
collection Online Access
language English
topic Q300 Cybernetics
T Technology (General)
spellingShingle Q300 Cybernetics
T Technology (General)
Morshidi, Malik Arman
Tjahjadi, Tardi
Gravity optimised particle filter for hand tracking
description This paper presents a gravity optimised particle filter (GOPF) where the magnitude of the gravitational force for every particle is proportional to its weight. GOPF attracts nearby particles and replicates new particles as if moving the particles towards the peak of the likelihood distribution, improving the sampling efficiency. GOPF is incorporated into a technique for hand features tracking. A fast approach to hand features detection and labelling using convexity defects is also presented. Experimental results show that GOPF outperforms the standard particle filter and its variants, as well as state-of-the-art CamShift guided particle filter using a significantly reduced number of particles.
format Article
author Morshidi, Malik Arman
Tjahjadi, Tardi
author_facet Morshidi, Malik Arman
Tjahjadi, Tardi
author_sort Morshidi, Malik Arman
title Gravity optimised particle filter for hand tracking
title_short Gravity optimised particle filter for hand tracking
title_full Gravity optimised particle filter for hand tracking
title_fullStr Gravity optimised particle filter for hand tracking
title_full_unstemmed Gravity optimised particle filter for hand tracking
title_sort gravity optimised particle filter for hand tracking
publisher Elsevier
publishDate 2014
url http://irep.iium.edu.my/35420/
http://irep.iium.edu.my/35420/
http://irep.iium.edu.my/35420/
http://irep.iium.edu.my/35420/1/Gravity_Optimised_Particle_Filter_for_Hand_Tracking.pdf
first_indexed 2023-09-18T20:50:47Z
last_indexed 2023-09-18T20:50:47Z
_version_ 1777409979695759360

Similar Items