• DocumentCode
    2626122
  • Title

    Optical flow A combined local-global approach using L1 norm

  • Author

    Drulea, Marius ; Peter, Ioan Radu ; Nedevschi, Sergiu

  • Author_Institution
    Comput. Sci. Dept., Tech. Univ. of Cluj-Napoca, Cluj-Napoca, Romania
  • fYear
    2010
  • fDate
    26-28 Aug. 2010
  • Firstpage
    217
  • Lastpage
    222
  • Abstract
    One of the most important step in precisely optical flow computation is using L1 norm for mathematical modeling. For discrete signals, L1 norm gives better results than L2. Another useful ingredient is using local and global combinations in order to use the advantages of both methods. We will present a combined local-global approach that uses L1 norm for both the data fidelity terms and the regularization one. Our approach is robust to noise and occlusions and preserves motion boundaries. Additionally, a version using L1 only for the regularization term and another one using only L2 are presented. We will show that combined local-global estimators have some benefits in real scenarios. All numerical schemes resulted are highly parallelizable, being designed for running on graphic processing units.
  • Keywords
    computer graphic equipment; coprocessors; image sequences; mathematical analysis; L1 norm; combined local global approach; graphic processing units; mathematical modeling; optical flow; Adaptive optics; Computer vision; Equations; Image motion analysis; Jacobian matrices; Mathematical model; Optical imaging;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Computer Communication and Processing (ICCP), 2010 IEEE International Conference on
  • Conference_Location
    Cluj-Napoca
  • Print_ISBN
    978-1-4244-8228-3
  • Electronic_ISBN
    978-1-4244-8230-6
  • Type

    conf

  • DOI
    10.1109/ICCP.2010.5606437
  • Filename
    5606437