• DocumentCode
    3177109
  • Title

    Discovering structural regularity in facade image

  • Author

    Li, Weiwei ; Zheng, Xin ; Chen, Jie

  • Author_Institution
    Image Process. & Pattern Recognition Lab., Beijing Normal Univ., Beijing, China
  • fYear
    2010
  • fDate
    10-13 Oct. 2010
  • Firstpage
    2208
  • Lastpage
    2212
  • Abstract
    3D reconstruction from single view is a very difficult problem in computer vision and computer graphics. Few works have been done in this area. In this paper, we proposed a method to discover structural regularity in single facade images on the procedural modeling of buildings by using SIFT algorithm. Firstly, symmetry information is detected from the image using SIFT algorithm for image analysis. Next, the symmetry information will be removed from the facade image. Finally, get the SIFT feature of widows and doors. Experiments show that our method can successfully discover regular structures with a higher recognition rate than existing method especially amidst shadowing and the changing illumination environment.
  • Keywords
    computer graphics; computer vision; image recognition; image reconstruction; transforms; 3D reconstruction; SIFT algorithm; computer graphics; computer vision; facade image; procedural modeling; recognition rate; structural regularity; symmetry information detection; Laboratories; 3D reconstruction; Facade Detection; SIFT; procedural modeling;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Systems Man and Cybernetics (SMC), 2010 IEEE International Conference on
  • Conference_Location
    Istanbul
  • ISSN
    1062-922X
  • Print_ISBN
    978-1-4244-6586-6
  • Type

    conf

  • DOI
    10.1109/ICSMC.2010.5641686
  • Filename
    5641686