Show simple item record

dc.contributor.authorLu, Y
dc.contributor.authorLi, Ling
dc.contributor.authorPeursum, Patrick
dc.contributor.editorMian, A. S. & Tan, T. (Program Chairs)
dc.date.accessioned2017-01-30T13:48:04Z
dc.date.available2017-01-30T13:48:04Z
dc.date.created2015-03-03T20:17:35Z
dc.date.issued2012
dc.identifier.citationLu, Y. and Li, L. and Peursum, P. 2012. Background suppression for building accurate appearance models in human motion tracking, in The International Conference on Digital Image Computing Techniques and Applications (DICTA), Dec 3-5 2012, pp. 215-220. Perth, WA: Institute of Electrical and Electronics Engineers (IEEE).
dc.identifier.urihttp://hdl.handle.net/20.500.11937/35165
dc.identifier.doi10.1109/DICTA.2012.6411695
dc.description.abstract

This paper presents a robust and fully-automatic human motion tracking system without motion priors information using a camera in a fixed location. Bottom-up estimation approaches have recently been applied to such tasks with some success. However, the performance of these approaches is limited by the difficulty of building an effective appearance model. In particular, the appearance model must be derived from initial estimates of the tracked person's limb posture. However, in addition to inaccuracies in this initial estimate, the precise shape, size and boundaries of the tracked person's limbs are not known. Hence it is inevitable that background (non-limb) pixels are included into the appearance model. In the case of smaller limbs such as the arms, this can cause the model to become unrepresentative and sometimes confused with other body parts such as the torso. In this paper, we address the problem of how to automatically extract accurate training samples for building an accurate appearance model, and propose a mechanism for identifying and removing background (negative) pixels via pixel clustering that is robust even with a loose-fitting body shape model. Experiments are conducted to compare the proposed approach against existing appearance-based algorithms without negative pixel removal using several publicly available data sets. Results show that tracking accuracy is consistently improved, and significantly so for small limbs such as the arms.

dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.titleBackground suppression for building accurate appearance models in human motion tracking
dc.typeConference Paper
dcterms.source.startPage215
dcterms.source.endPage220
dcterms.source.title2012 International Conference on Digital Image Computing Techniques and Applications (DICTA)
dcterms.source.series2012 International Conference on Digital Image Computing Techniques and Applications (DICTA)
dcterms.source.isbn9781467321815
dcterms.source.conferenceThe International Conference on Digital Image Computing: Techniques and Applications (DICTA 2012)
dcterms.source.conference-start-dateDec 3 2012
dcterms.source.conferencelocationPerth, WA
dcterms.source.placeNot known
curtin.departmentDepartment of Computing
curtin.accessStatusFulltext not available


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record