We present a Bayesian network based multimodal fusion method for robust and real-time face tracking. The Bayesian network integrates a prior of second order system dynamics, and the likelihood cues from color, edge and face appearance. While different modalities have different confidence scales, we encode the environmental factors related to the confidences of modalities into the Bayesian network, and develop a Fisher discriminant analysis method for learning optimal fusion. The face tracker may track multiple faces under different poses. It is made up of two stages. First hypotheses are efficiently generated using a coarse-to-fine strategy; then multiple modalities are integrated in the Bayesian network to evaluate the posterior of each hypothesis. The hypothesis that maximizes a posterior (MAP) is selected as the estimate of the object state. Experimental results demonstrate the robustness and real-time performance of our face tracking approach.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-modal face tracking using Bayesian network


    Contributors:
    Fang Liu, (author) / Xueyin Lin, (author) / Li, S.Z. (author) / Yuanchun Shi, (author)


    Publication date :

    2003-01-01


    Size :

    469753 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multi-Modal Face Tracking Using Bayesian Network

    Liu, F. / Lin, X. / Li, S. et al. | British Library Conference Proceedings | 2003


    Tracking Humans using Multi-modal Fusion

    Xiaotao Zou, / Bhanu, B. | IEEE | 2005


    Multi-modal tracking using texture changes

    Kemp, C. / Drummond, T. | British Library Online Contents | 2008


    Multi-Modal Real-World Driving Data Collection, Transcription, and Integration Using Bayesian Network

    Malta, L. / Angkititrakul, P. / Miyajima, C. et al. | British Library Conference Proceedings | 2008


    Multi-modal real-world driving data collection, transcription, and integration using Bayesian Network

    Malta, Lucas / Angkititrakul, Pongtep / Miyajima, Chiyomi et al. | IEEE | 2008