Skip navigation
Skip navigation

Using an adaptive VAR model for motion prediction in 3D hand tracking

Chik, Desmond; Trumpf, Jochen; Schraudolph, Nic

Description

A robust VAR-based (vector autoregressive) model is introduced for motion prediction in 3D hand tracking. This dynamic VAR motion model is learned in an online manner. The kinematic structure of the hand is accounted for in the form of constraints when solving for the parameters of the VAR model. Also integrated into the motion prediction model are adaptive weights that are optimised according to the reliability of past predictions. Experiments on synthetic and real video sequences show a...[Show more]

dc.contributor.authorChik, Desmond
dc.contributor.authorTrumpf, Jochen
dc.contributor.authorSchraudolph, Nic
dc.coverage.spatialAmsterdam Netherlands
dc.date.accessioned2015-12-07T22:47:44Z
dc.date.available2015-12-07T22:47:44Z
dc.date.createdSeptember 17-19 2008
dc.identifier.isbn9781424421541
dc.identifier.urihttp://hdl.handle.net/1885/26175
dc.description.abstractA robust VAR-based (vector autoregressive) model is introduced for motion prediction in 3D hand tracking. This dynamic VAR motion model is learned in an online manner. The kinematic structure of the hand is accounted for in the form of constraints when solving for the parameters of the VAR model. Also integrated into the motion prediction model are adaptive weights that are optimised according to the reliability of past predictions. Experiments on synthetic and real video sequences show a substantial improvement in tracking performance when the robust VAR motion model is used. In fact, utilising the robust VAR model allows the tracker to handle fast out-of-plane hand movement with severe self-occlusion.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)
dc.relation.ispartofseriesInternational Conference on Automatic Face and Gesture Recognition 2008
dc.sourceProceedings of International Conference on Automatic Face and Gesture Recognition 2008
dc.source.urihttp://users.rsise.anu.edu.au/~desmondc/chik08.pdf
dc.subjectKeywords: 3D hand tracking; Adaptive weights; Auto-regressive; Hand movement; Kinematic structures; Motion models; Motion prediction; Out-of-plane; Real video sequences; Self occlusion; Tracking performance; Face recognition; Mathematical models; Three dimensional;
dc.titleUsing an adaptive VAR model for motion prediction in 3D hand tracking
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2008
local.identifier.absfor080104 - Computer Vision
local.identifier.absfor080109 - Pattern Recognition and Data Mining
local.identifier.absfor090600 - ELECTRICAL AND ELECTRONIC ENGINEERING
local.identifier.ariespublicationu2505865xPUB43
local.identifier.ariespublicationf5625xPUB12829
local.type.statusPublished Version
local.contributor.affiliationChik, Desmond, College of Engineering and Computer Science, ANU
local.contributor.affiliationTrumpf, Jochen, College of Engineering and Computer Science, ANU
local.contributor.affiliationSchraudolph, Nic, Adaptive Tools AG
local.bibliographicCitation.startpage8
local.identifier.doi10.1109/AFGR.2008.4813414
dc.date.updated2016-02-24T09:51:03Z
local.identifier.scopusID2-s2.0-67650691103
CollectionsANU Research Publications

Download

There are no files associated with this item.


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  17 November 2022/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator