We present algorithms for recognizing human motion in monocular video sequences, based on discriminative conditional random field (CRF) and maximum entropy Markov models (MEMM). Existing approaches to this problem typically use generative (joint) structures like the hidden Markov model (HMM). Therefore they have to make simplifying, often unrealistic assumptions on the conditional independence of observations given the motion class labels and cannot accommodate overlapping features or long term contextual dependencies in the observation sequence. In contrast, conditional models like the CRFs seamlessly represent contextual dependencies, support efficient, exact inference using dynamic programming, and their parameters can be trained using convex optimization. We introduce conditional graphical models as complementary tools for human motion recognition and present an extensive set of experiments that show how these typically outperform HMMs in classifying not only diverse human activities like walking, jumping. running, picking or dancing, but also for discriminating among subtle motion styles like normal walk and wander walk.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Conditional models for contextual human motion recognition


    Beteiligte:
    Sminchisescu, C. (Autor:in) / Kanaujia, A. (Autor:in) / Zhiguo Li, (Autor:in) / Metaxas, D. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    873363 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Conditional models for contextual human motion recognition

    Sminchisescu, C. / Kanaujia, A. / Metaxas, D. | British Library Online Contents | 2006


    Conditional Models for Contextual Human Motion Recognitio

    Sminchisescu, C. / Kanaujia, A. / Li, Z. et al. | British Library Conference Proceedings | 2005


    Hybrid models for human motion recognition

    Fanti, C. / Zelnik-Manor, L. / Perona, P. | IEEE | 2005


    Conditional motion predictions

    ERIC WOLFF / SAMMIE KATT / BENCE CSERNA | Europäisches Patentamt | 2023

    Freier Zugriff

    Conditional motion predictions

    Europäisches Patentamt | 2020

    Freier Zugriff