Show simple item record

dc.contributor.authorPeursum, Patrick
dc.contributor.authorVenkatesh, Svetha
dc.contributor.authorWest, Geoffrey
dc.date.accessioned2017-01-30T15:37:21Z
dc.date.available2017-01-30T15:37:21Z
dc.date.created2010-03-09T20:02:47Z
dc.date.issued2009
dc.identifier.citationPeursum, Patrick and Venkatesh, Svetha and West, Geoffrey. 2009. A study on smoothing for particle-filtered 3D human body tracking. International Journal of Computer Vision. 87 (1-2): pp. 53-74.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/48073
dc.identifier.doi10.1007/s11263-009-0205-5
dc.description.abstract

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.

dc.publisherSpringer Netherlands
dc.subjectSmoothing
dc.subjectParticle filtering
dc.subjectArticulated human body tracking
dc.titleA study on smoothing for particle-filtered 3D human body tracking
dc.typeJournal Article
dcterms.source.volume87
dcterms.source.number1-2
dcterms.source.startPage53
dcterms.source.endPage74
dcterms.source.issn09205691
dcterms.source.titleInternational Journal of Computer Vision
curtin.note

The original publication is available at : www.springerlink.com

curtin.accessStatusOpen access
curtin.facultySchool of Science and Computing
curtin.facultyDepartment of Computing
curtin.facultyFaculty of Science and Engineering


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record