• DocumentCode
    1814206
  • Title

    Active Net control for traffic signs detection

  • Author

    Yabuki, Noboru ; Matsuda, Yoshitaka ; Sumi, Yasuaki ; Fukui, Yutaka ; Miki, Shigehiko

  • Author_Institution
    Dept. of Electron. & Comput. Eng., Tsuyama Nat. Coll. of Technol., Okayama, Japan
  • fYear
    2001
  • fDate
    2001
  • Firstpage
    151
  • Lastpage
    155
  • Abstract
    In this paper, we propose a method for detecting a traffic sign from a scene image in the daytime. This method uses Active Net in two steps. Active net is a deformable lattice network model which minimizes an energy function to detect the region of a target object. In the proposed method, the first Active Net roughly estimates a position of a target region For the better target detection, we put the second Active Net around the estimated position. However, since the number of the iteration of Active Net is fixed, an unnecessary computation is performed in the method Therefore, a method to exclude unnecessary computation by automatic stopping of Active Net is also proposed. Experimental results show the effectiveness and efficiency of the proposed method
  • Keywords
    automated highways; feature extraction; parameter estimation; Active Net; binarized image; daytime; deformable lattice network model; energy function minimisation; intelligent transport systems; iteration; scene image; target object region detection; traffic sign detection; traffic signs extraction; Deformable models; Educational institutions; Gas detectors; Image edge detection; Information systems; Intelligent systems; Lattices; Layout; Object detection; Road accidents;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Vehicle Electronics Conference, 2001. IVEC 2001. Proceedings of the IEEE International
  • Conference_Location
    Tottori
  • Print_ISBN
    0-7803-7229-8
  • Type

    conf

  • DOI
    10.1109/IVEC.2001.961745
  • Filename
    961745