• DocumentCode
    3056554
  • Title

    Edge-preserving directional regularization technique for disparity estimation of stereoscopic images

  • Author

    Mi-Hyun Kim ; Kwang-Hoon Sohn

  • Author_Institution
    Dept. of Radio Commun. Eng., Yonsei Univ., Seoul, South Korea
  • fYear
    1999
  • fDate
    22-24 June 1999
  • Firstpage
    376
  • Lastpage
    377
  • Abstract
    This paper presents a new disparity estimation method using an edge-preserving directional regularization technique. This method smooths disparity vectors in smooth regions and preserves edges in object boundaries without oversmoothing. Very close matches between a left image and a right image are obtained as well as improved coding efficiency.
  • Keywords
    edge detection; image coding; smoothing methods; stereo image processing; coding efficiency; disparity estimation; disparity vectors; edge preservation; edge-preserving directional regularization technique; left image; object boundaries; right image; smooth regions; stereoscopic images; Biomedical imaging; Cost function; Entropy; Humans; Image coding; Image reconstruction; Layout; Manufacturing industries; Radio communication; Video compression;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Consumer Electronics, 1999. ICCE. International Conference on
  • Conference_Location
    Los Angeles, CA, USA
  • Print_ISBN
    0-7803-5123-1
  • Type

    conf

  • DOI
    10.1109/ICCE.1999.785421
  • Filename
    785421
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3056554