• DocumentCode
    666582
  • Title

    Rotation estimation for visual odometry using 3D vector correspondence

  • Author

    Jae Seok Jang ; Kwang Hee Won ; Soon Ki Jung

  • Author_Institution
    Sch. of Comput. Sci. & Eng., Kyungpook Nat. Univ., Daegu, South Korea
  • fYear
    2013
  • fDate
    10-13 Nov. 2013
  • Firstpage
    5512
  • Lastpage
    5515
  • Abstract
    Visual odometry is important to obtain the vehicle motion as well as the relative motion of the surroundings such as moving/stationary objects to the vehicle. This paper presents a vehicle motion estimation approach which uses 3D vector correspondences. We design an objective function using 3D vector registration error and optimize it. The proposed method estimates more accurate rotation matrix compared to the previous method.
  • Keywords
    image registration; motion estimation; object detection; rotation measurement; stereo image processing; 3D vector correspondence; 3D vector registration error; rotation estimation; vehicle motion estimation; visual odometry; Accuracy; Estimation; Feature extraction; Three-dimensional displays; Vectors; Vehicles; Visualization; vehicle motion estimation; visual odometry;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Industrial Electronics Society, IECON 2013 - 39th Annual Conference of the IEEE
  • Conference_Location
    Vienna
  • ISSN
    1553-572X
  • Type

    conf

  • DOI
    10.1109/IECON.2013.6700035
  • Filename
    6700035