Now showing items 1-5 of 5

  • Automatic learning of 3D pose variability in walking performances for gait analysis 

    Rius, Ignasi; Gonzàlez, Jordi; Mozerov, Mikhail; Roca, Francesc Xavier (Serials Publications, 2008)
    Article
    Open Access
    This paper proposes an action specific model which automatically learns the variability of 3D human postures observed in a set of training sequences. First, a Dynamic Programing synchronization algorithm is presented in ...
  • Automatic learning of 3D pose variability in walking performances for gait analysis 

    Rius, Ignasi; González Sabaté, Jordi; Mozerov, Mikhail; Roca, Francesc Xavier (2008)
    Article
    Open Access
    This paper proposes an action specific model which automatically learns the variability of 3D human postures observed in a set of training sequences. First, a Dynamic Programing synchronization algorithm is presented in ...
  • Component-based human detection 

    Chakraborty, Bhaskar; Rius, Ignasi; Perdersoli, Marco; Mozerov, Mikhail; Gonzàlez, Jordi (s. n., 2007)
    Conference report
    Open Access
    In this paper, we present a general framework for human detection in a video sequence by components. The technique is demonstrated by developing a system that locates people in the cluttered scenes where they are performing ...
  • Hierarchical eyelid and face tracking 

    Orozco, Francisco J.; Gonzàlez, Jordi; Rius, Ignasi; Roca, Francesc Xavier (Springer Verlag, 2007)
    Part of book or chapter of book
    Open Access
    Most applications on Human Computer Interaction (HCI) require to extract the movements of user faces, while avoiding high memory and time expenses. Moreover, HCI systems usually use low-cost cameras, while current face ...
  • Importance of detection for video surveillance applications 

    Varona, Javier; González Sabaté, Jordi; Rius, Ignasi; Villanueva Pipaón, Juan José (2008)
    Article
    Open Access
    Though it is the first step of a real video surveillance application, detection has received less attention than tracking in research on video surveillance. We show, however, that the majority of errors in the tracking ...