• DocumentCode
    1968809
  • Title

    A Robust Feature-Based Camera Motion Estimation Method

  • Author

    Xiao-chun Zou ; Ming-yi He ; Xin-bo Zhao ; Yan Feng

  • Author_Institution
    Sch. of Electron. & Inf., Northwestern Polytech. Univ., Xi´an, China
  • fYear
    2010
  • fDate
    30-31 Jan. 2010
  • Firstpage
    50
  • Lastpage
    53
  • Abstract
    The camera motion that is caused by the moving camera is one of two types of video motion. The feature-based techniques are known to perform more robust with large motion. The research of such a robust feature-based camera motion estimation method is necessary and possible. In this paper, a robust feature-based camera motion estimation method is proposed. The algorithm uses the motion vectors obtained from a set of selected points to calculate the parameters of the camera motion model. It comprises three steps: the detection of feature points, the computation of correspondences between two sets of features, and the motion parameter estimation. This whole process ensures that only the motion model that had the largest number of inliers is returned as result. Experimental results show the proposed method can be successfully provided with the camera motion estimation capability.
  • Keywords
    image sensors; motion estimation; parameter estimation; video signal processing; feature points detection; feature-based techniques; motion parameter estimation; motion tracking; robust feature-based camera motion estimation method; video motion; Cameras; Computer vision; Helium; Information technology; Motion detection; Motion estimation; Noise robustness; Oceans; Parameter estimation; Underwater communication; feature correspondences; feature points detection; motion estimation; motion tracking;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Innovative Computing & Communication, 2010 Intl Conf on and Information Technology & Ocean Engineering, 2010 Asia-Pacific Conf on (CICC-ITOE)
  • Conference_Location
    Macao
  • Print_ISBN
    978-1-4244-5634-5
  • Electronic_ISBN
    978-1-4244-5635-2
  • Type

    conf

  • DOI
    10.1109/CICC-ITOE.2010.20
  • Filename
    5439293