We propose a framework for learning robust, adaptive appearance models to be used for motion-based tracking of natural objects. The approach involves a mixture of stable image structure, learned over long time courses, along with 2-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motion-based tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions. It also provides the ability to adapt to natural changes in appearance, such as those due to facial expressions or variations in 3D pose. We show experimental results on a variety of natural image sequences of people moving within cluttered environments.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Robust online appearance models for visual tracking


    Contributors:


    Publication date :

    2001-01-01


    Size :

    1525892 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Robust Online Appearance Models for Visual Tracking

    Jepson, A. D. / Fleet, D. J. / El-Maraghi, T. F. et al. | British Library Conference Proceedings | 2001


    Online learning and fusion of orientation appearance models for robust rigid object tracking

    Marras, I. / Tzimiropoulos, G. / Zafeiriou, S. et al. | British Library Online Contents | 2014


    Online multi-object tracking by detection based on generative appearance models

    Riahi, Dorra / Bilodeau, Guillaume-Alexandre | British Library Online Contents | 2016


    Online multi-object tracking by detection based on generative appearance models

    Riahi, Dorra / Bilodeau, Guillaume-Alexandre | British Library Online Contents | 2016


    Pose Robust Face Tracking by Combining Active Appearance Models and Cylinder Head Models

    Sung, J. / Kanade, T. / Kim, D. | British Library Online Contents | 2008