• DocumentCode
    2668922
  • Title

    Velocity based vestibular-visual integration in active sensing system

  • Author

    Yamaguchi, Teruo ; Yamasaki, Hiro

  • Author_Institution
    Dept. of Mech. Eng., Kumamoto Univ., Japan
  • fYear
    1994
  • fDate
    2-5 Oct 1994
  • Firstpage
    639
  • Lastpage
    646
  • Abstract
    It is necessary for most of advanced visual sensing systems to realize visual stabilization and target gazing prior to recognition process when operating in a structurally unconstrained environment. In this paper, a new method of acquiring that fundamental ability by sensor fusion technique is proposed. It is important to choose an appropriate sensor fusion basis, and it is proposed to integrate the visual system with angular velocity sensors and a gaze control system by one of those constraint conditions which govern the relation between measured and control variables. It is also proposed that such a visual sensing system is realized by integrating the systems through their (angular) velocity information. Because the velocity field in the image can be now calculated in real time and the angular velocity can be treated directly by both rate gyroscopes and gaze control motors, such an integration is expected to fit for the visual system which requires quick response. Experimental results show that proposed velocity based visual stabilization is feasible and exhibits better performance than that solely by a single sensation. The reason accounting for this improvement is also theoretically discussed
  • Keywords
    active vision; computer vision; image recognition; sensor fusion; velocity measurement; active sensing system; angular velocity sensors; gaze control motors; rate gyroscopes; recognition process; sensor fusion; structurally unconstrained environment; target gazing; velocity field; velocity-based vestibular-visual integration; velocity-based visual stabilization; Angular velocity; Angular velocity control; Control systems; Gyroscopes; Real time systems; Sensor fusion; Sensor systems; Target recognition; Velocity measurement; Visual system;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multisensor Fusion and Integration for Intelligent Systems, 1994. IEEE International Conference on MFI '94.
  • Conference_Location
    Las Vegas, NV
  • Print_ISBN
    0-7803-2072-7
  • Type

    conf

  • DOI
    10.1109/MFI.1994.398394
  • Filename
    398394