We present a method for online rigid object tracking using an adaptive view-based appearance model. When the object's pose trajectory crosses itself, our tracker has bounded drift and can track objects undergoing large motion for long periods of time. Our tracker registers each incoming frame against the views of the appearance model using a two-frame registration algorithm. Using a linear Gaussian filter, we simultaneously estimate the pose of the object and adjust the view-based model as pose-changes are recovered from the registration algorithm. The adaptive view-based model is populated online with views of the object as it undergoes different orientations in pose space, allowing us to capture non-Lambertian effects. We tested our approach on a real-time rigid object tracking task using stereo cameras and observed an RMS error within the accuracy limit of an attached inertial sensor.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Adaptive view-based appearance models


    Contributors:
    Morency, L.-P. (author) / Rahimi, A. (author) / Darrell, T. (author)


    Publication date :

    2003-01-01


    Size :

    6319682 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Adaptive View-Based Appearance Models

    Morency, L.-P. / Rahimi, A. / Darrell, T. et al. | British Library Conference Proceedings | 2003


    View-based active appearance models

    Cootes, T. F. / Wheeler, G. V. / Walker, K. N. et al. | British Library Online Contents | 2002


    Monocular head pose estimation using generalized adaptive view-based appearance model

    Morency, L. P. / Whitehill, J. / Movellan, J. | British Library Online Contents | 2010


    Direct appearance models

    XinWen Hou, / Li, S.Z. / HongJiang Zhang, et al. | IEEE | 2001


    Direct Appearance Models

    Hou, X. W. / Li, S. Z. / Zhang, H. J. et al. | British Library Conference Proceedings | 2001