• DocumentCode
    2610329
  • Title

    Vehicle Lateral Position Estimation Method Based on Matching of Top-View Images

  • Author

    Teshima, Tomoaki ; Saito, Hideo ; Ozawa, Shinji ; Yamamoto, Keiichi ; Ihara, Toru

  • Author_Institution
    Dept. of Inf. & Comput. Sci., Keio Univ., Yokohama
  • Volume
    4
  • fYear
    0
  • fDate
    0-0 0
  • Firstpage
    626
  • Lastpage
    629
  • Abstract
    In this paper, a method to estimate the lateral position of the vehicle from a sequence of moving camera images is proposed. Proposed method relies on the plane projective transform (homography) between the ground and the image plane of the present and the next frame. Homographies are obtained according to the information of the calibrated camera and the vehicles´ speed. The movement of the camera is obtained by the registration of the 2 consecutive input images. The proposed method does not rely on extraction of features such as lines, flow vectors or lane markers, but based on matching of warped top-view images between two consecutive frames. Therefore, vehicle movement can be estimated even from images without such explicit image features or without special sensors or GPS. In this paper, experiments are done with both synthesized and real images and enough accuracy is shown even compared to conventional method
  • Keywords
    edge detection; feature extraction; image matching; image registration; image sequences; motion estimation; road vehicles; traffic engineering computing; transforms; feature extraction; flow vectors; homography; image registration; lane markers; moving camera image sequence; plane projective transform; top-view image matching; vehicle lateral position estimation; Cameras; Computer science; Global Positioning System; Image converters; Image motion analysis; Image sensors; Mobile robots; Optical sensors; Remotely operated vehicles; Vehicle driving;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
  • Conference_Location
    Hong Kong
  • ISSN
    1051-4651
  • Print_ISBN
    0-7695-2521-0
  • Type

    conf

  • DOI
    10.1109/ICPR.2006.1166
  • Filename
    1699919