Using an adaptive var model for motion prediction in 3d hand tracking

Desmond Chik*, Jochen Trumpf, Nicol N. Schraudolph

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    1 Citation (Scopus)

    Abstract

    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 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.

    Original languageEnglish
    Title of host publication2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
    DOIs
    Publication statusPublished - 2008
    Event2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 - Amsterdam, Netherlands
    Duration: 17 Sept 200819 Sept 2008

    Publication series

    Name2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008

    Conference

    Conference2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
    Country/TerritoryNetherlands
    CityAmsterdam
    Period17/09/0819/09/08

    Fingerprint

    Dive into the research topics of 'Using an adaptive var model for motion prediction in 3d hand tracking'. Together they form a unique fingerprint.

    Cite this