• DocumentCode
    2958342
  • Title

    Physically-based motion models for 3D tracking: A convex formulation

  • Author

    Salzmann, Mathieu ; Urtasun, Raquel

  • Author_Institution
    TTI-Chicago, Chicago, IL, USA
  • fYear
    2011
  • fDate
    6-13 Nov. 2011
  • Firstpage
    2064
  • Lastpage
    2071
  • Abstract
    In this paper, we propose a physically-based dynamical model for tracking. Our model relies on Newton´s second law of motion, which governs any real-world dynamical system. As a consequence, it can be generally applied to very different tracking problems. Furthermore, since the equations describing Newton´s second law are simple linear equalities, they can be incorporated in any tracking framework at very little cost. Leveraging this lets us introduce a convex formulation of 3D tracking from monocular images. We demonstrate the strengths of our approach on various types of motion, such as billiards and acrobatics.
  • Keywords
    convex programming; image motion analysis; linear matrix inequalities; object tracking; 3D tracking framework; Newton second law of motion; convex formulation; linear equalities; monocular images; physically-based motion model; real-world dynamical system; Computational modeling; Gravity; Humans; Markov processes; Mathematical model; Three dimensional displays; Tracking;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision (ICCV), 2011 IEEE International Conference on
  • Conference_Location
    Barcelona
  • ISSN
    1550-5499
  • Print_ISBN
    978-1-4577-1101-5
  • Type

    conf

  • DOI
    10.1109/ICCV.2011.6126480
  • Filename
    6126480