Show simple item record

dc.contributor.authorPeursum, Patrick
dc.contributor.authorVenkatesh, Svetha
dc.contributor.authorWest, Geoffrey
dc.identifier.citationPeursum, Patrick and Venkatesh, Svetha and West, Geoffrey. 2007. : Tracking-as-Recognition for Articulated Full-Body Human Motion Analysis, IEEE Conference on Computer Vision and Patter Recognition 2007, 17 Jun 2007. Minneapolis, USA: IEEE Computer Society Conference Publishing Services.

This paper addresses the problem of markerless tracking of a human in full 3D with a high-dimensional (29D) body model. Most work in this area has been focused on achieving accurate tracking in order to replace marker-based motion capture, but do so at the cost of relying on relatively clean observing conditions. This paper takes a different perspective, proposing a body-tracking model that is explicitly designed to handle real-world conditions such as occlusions by scene objects, failure recovery, long-term tracking, auto-initialisation, generalisation to different people and integration with action recognition. To achieve these goals, an action's motions are modelled with a variant of the hierarchical hidden Markov model. The model is quantitatively evaluated with several tests, including comparison to the annealed particle filter, tracking different people and tracking with a reduced resolution and frame rate.

dc.publisherIEEE Computer Society Conference Publishing Services
dc.titleTracking-as-Recognition for Articulated Full-Body Human Motion Analysis
dc.typeConference Paper
dcterms.source.titleComputer Vision and Pattern Recognition 2007
dcterms.source.seriesComputer Vision and Pattern Recognition 2007
dcterms.source.conferenceIEEE Conference on Computer Vision and Patter Recognition 2007
dcterms.source.conference-start-date17 Jun 2007
dcterms.source.conferencelocationMinneapolis, USA
curtin.accessStatusOpen access
curtin.facultyFaculty of Engineering and Computing
curtin.facultyDivision of Engineering, Science and Computing
curtin.facultyDepartment of Computing

Files in this item


This item appears in the following Collection(s)

Show simple item record