Now showing items 1-4 of 4

    • GMM background modeling using divergence-based weight updating 

      Pulgarin Giraldo, Juan Diego; Castellanos Dominguez, German; Insuasti Ceballos, Hernan David; Álvarez Meza, Andrés Marino; Bouvmans, Thierry (Springer, Cham, 2017-02-16)
      Background modeling is a core task of video-based surveillance systems used to facilitate the online analysis of real-world scenes. Nowadays, GMM-based background modeling approaches are widely used, and several versions ...
    • Relevant kinematic feature selection to support human action recognition in MoCap data 

      Pulgarin Giraldo, Juan Diego; Alvarez Meza, Andres Marino; Ruales Tores, A. A.; Castellanos Dominguez, German (Springer, Cham, 2017)
      This paper presents a feature selection comparison oriented to human action recognition only with the kinematic features of skeleton representation. For this purpose, three relevance methods are used to rank the contribution ...
    • Relevant Kinematic Feature Selection to Support Human Action Recognition in MoCap data 

      Pulgarin Giraldo, Juan Diego; Alvarez Meza, Andres Marino; Ruales Tores, A. A.; Castellanos Dominguez, German (Springer, Cham, 2017-05-27)
      This paper presents a feature selection comparison oriented to human action recognition only with the kinematic features of skeleton representation. For this purpose, three relevance methods are used to rank the contribution ...
    • A similarity indicator for differentiating kinematic performance between qualified tennis players 

      Pulgarin Giraldo, Juan Diego; Castellanos Dominguez, German; Melo Betancourt, Luis Gerardo; Álvarez Meza, Andrés Marino; Ramos Bermudez, Santiago (Springer, Cham, 2017-02-16)
      This paper presents a data-driven approach to estimate the kinematic performance of tennis players, using kernels to extract a dynamic model of each player from motion capture (MoCap) data. Thus, a metric is introduced in ...