A study on smoothing for particle-filtered 3D human body tracking

Stochastic models have become the dominant means of approaching the problem of articulated 3D human body tracking, where approximate inference is employed to tractably estimate the high-dimensional (~30D) posture space. Of these approximate inference techniques, particle filtering is the most common...

Full description

Bibliographic Details
Main Authors: Peursum, Patrick, Venkatesh, Svetha, West, Geoffrey
Format: Journal Article
Published: Springer Netherlands 2009
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/48073
_version_ 1848758010053132288
author Peursum, Patrick
Venkatesh, Svetha
West, Geoffrey
author_facet Peursum, Patrick
Venkatesh, Svetha
West, Geoffrey
author_sort Peursum, Patrick
building Curtin Institutional Repository
collection Online Access
description Stochastic models have become the dominant means of approaching the problem of articulated 3D human body tracking, where approximate inference is employed to tractably estimate the high-dimensional (~30D) posture space. Of these approximate inference techniques, particle filtering is the most commonly used approach. However filtering only takes into account past observations - almost no body tracking research employs smoothing to improve the filtered inference estimate, despite the fact that smoothing considers both past and future evidence and so should be more accurate. In an effort to objectively determine the worth of existing smoothing algorithms when applied to human body tracking, this paper investigates three approximate smoothed-inference techniques: particle-filtered backwards smoothing, variational approximation and Gibbs sampling. Results are quantitatively evaluated on both the HUMANEVA dataset as well as a scene containing occluding clutter. Surprisingly, it is found that existing smoothing techniques are unable to provide much improvement on the filtered estimate, and possible reasons as to why are explored and discussed.
first_indexed 2025-11-14T09:37:11Z
format Journal Article
id curtin-20.500.11937-48073
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:37:11Z
publishDate 2009
publisher Springer Netherlands
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-480732017-09-13T15:59:12Z A study on smoothing for particle-filtered 3D human body tracking Peursum, Patrick Venkatesh, Svetha West, Geoffrey Smoothing Particle filtering Articulated human body tracking Stochastic models have become the dominant means of approaching the problem of articulated 3D human body tracking, where approximate inference is employed to tractably estimate the high-dimensional (~30D) posture space. Of these approximate inference techniques, particle filtering is the most commonly used approach. However filtering only takes into account past observations - almost no body tracking research employs smoothing to improve the filtered inference estimate, despite the fact that smoothing considers both past and future evidence and so should be more accurate. In an effort to objectively determine the worth of existing smoothing algorithms when applied to human body tracking, this paper investigates three approximate smoothed-inference techniques: particle-filtered backwards smoothing, variational approximation and Gibbs sampling. Results are quantitatively evaluated on both the HUMANEVA dataset as well as a scene containing occluding clutter. Surprisingly, it is found that existing smoothing techniques are unable to provide much improvement on the filtered estimate, and possible reasons as to why are explored and discussed. 2009 Journal Article http://hdl.handle.net/20.500.11937/48073 10.1007/s11263-009-0205-5 Springer Netherlands fulltext
spellingShingle Smoothing
Particle filtering
Articulated human body tracking
Peursum, Patrick
Venkatesh, Svetha
West, Geoffrey
A study on smoothing for particle-filtered 3D human body tracking
title A study on smoothing for particle-filtered 3D human body tracking
title_full A study on smoothing for particle-filtered 3D human body tracking
title_fullStr A study on smoothing for particle-filtered 3D human body tracking
title_full_unstemmed A study on smoothing for particle-filtered 3D human body tracking
title_short A study on smoothing for particle-filtered 3D human body tracking
title_sort study on smoothing for particle-filtered 3d human body tracking
topic Smoothing
Particle filtering
Articulated human body tracking
url http://hdl.handle.net/20.500.11937/48073