• DocumentCode
    1585701
  • Title

    Design and experiment of distance measuring system with single camera for picking robot

  • Author

    Yu, Jinwei ; Song, Jian ; Sun, Xueyan ; Zhang, Tiezhong

  • Author_Institution
    Coll. of Machinery, Weifang Univ., Weifang, China
  • fYear
    2010
  • Firstpage
    445
  • Lastpage
    448
  • Abstract
    The task of vision system is to discern and position the target from growing environment for vegetables picking robot and provide kinematical parameter for the manipulator. Distance measuring is not only an important factor in influencing the positioning accuracy of picking target but also a difficulty for in the research of picking robot. For this reason, a new method of measuring distance by means of single camera for picking robot is suggested. The dual threshold is adopted to segment the G-B gray images of the target. The object´s characters, such as outline, area, center of gravity, enclosing rectangle and the point to cut off, are distilled through contour tracing. The width d of eggplant image at two location and the motion distance of the manipulator along optical axis are obtained separately, and then the distance z between the camera and the eggplant. Testing soft is programmed based on Visual C++ 6.0 according to the measuring distance theory. Experiments explain that the measure error is within ±18mm when the measure distance ranges from 275mm to 575mm.
  • Keywords
    agricultural products; distance measurement; image colour analysis; image segmentation; manipulator kinematics; position control; robot programming; robot vision; G-B gray image; Visual C++ 6.0; distance measuring system; eggplant image; manipulator kinematics; motion distance; positioning accuracy; robot programming; single camera; target position; testing soft; vegetable picking robot; vision system; Cameras; Image segmentation; Measurement uncertainty; Pixel; Robot kinematics; Robot vision systems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    World Automation Congress (WAC), 2010
  • Conference_Location
    Kobe
  • ISSN
    2154-4824
  • Print_ISBN
    978-1-4244-9673-0
  • Electronic_ISBN
    2154-4824
  • Type

    conf

  • Filename
    5665279