You are signed in as:
  • IFPRI
  • Signed in via:
  • IP Address

  • Choose a colour
  • Automation of unloading grain cars using the "Grain-o-Bot".

    Author(s) : Mohan, A. L.Jayas, D. S.

    Author Affiliation : Department of Biosystems Engineering, University of Manitoba, Winnipeg, 207 Administrative Building, Manitoba R3T 2N2, Canada.

    Author Email : Digvir.Javas@umanitoba.ca

    Journal article : Transactions of the ASABE 2013 Vol.56 No.5 pp.1837-1845 ref.22

    Abstract : Large quantities of bulk graingrainSubject Category: Commodities and Products
    see more details
    are moved using railway grain cars in Canada and other parts of the world. AutomationautomationSubject Category: Miscellaneous
    see more details
    has not progressed significantly in the grain industry, most probably because the market is limited for automated systems. A prototype of a robot ("Grain-o-bota") using machine visionmachine visionSubject Category: TechniquestechniquesSubject Category: Techniques, Methodologies and Equipment
    see more details
    , Methodologies and Equipment

    see more details
    to automatically open and close the grain car hopper gates and detect the contents of the grain car was built and studied. The "Grain-o-bota" was a Cartesian robot equipped with two camerascamerasSubject Category: Techniques, Methodologies and Equipment
    see more details
    and an opening tool as the end-effector. One camera acted as the eye to determine the hopper gate sprocket location and guide the end-effector to the sprocket opening. Most reported applications have used machine vision solutions based on pattern recognition, and these were developed using images acquired in a laboratory setting. Major constraints with these solutions occurred when implementing them in real-world applications, as ambient lightlightSubject Category: Miscellaneous
    see more details
    is a hindrance. So the first step for this automation was to correctly identify the hopper gate sprocket on the grain car. AlgorithmsalgorithmsSubject Category: Techniques, Methodologies and Equipment
    see more details
    were developed to detect and identify the sprocket under proper lighting conditions with 100% accuracy. The performance of the algorithms was also evaluated for identification of the sprocket in different lighting conditions, which are expected to occur in typical grain unloadingunloadingSubject Category: Techniques, Methodologies and Equipment
    see more details
    facilities. Monochrome images of the sprocket from a model system were acquired using different lights. Correlation and pattern recognition techniques using a template image combined with shape detection were used for sprocket identification. Prior to template matching, the images were preprocessed using image processingimage processingSubject Category: Techniques, Methodologies and Equipment
    see more details
    techniques. The template image developed from the light source that was similar to the light source used to acquire images was more successful in identifying the sprocket than the template image developed using different light sources. A sample of the grain car contents was taken by slightly opening and immediately closing the hopper gate. The sample was identified by taking an image using the second camera and performing feature matching. An accuracy of 99.9% was achieved in identifying Canada Western Red Spring (CWRS) and canola, and 100% accuracy was achieved in identifying barley.

    ISSN : 2151-0032

    URL : http://www.asabe.org/

    Record Number : 20143011596

    Publisher : American Society of Agricultural and Biological Engineers

    Location of publication : St Joseph

    Country of publication : USA

    Language of text : English

    Indexing terms for this abstract:

    Descriptor(s) : algorithmsalgorithmsSubject Category: Techniques, Methodologies and Equipment
    see more details
    , automatic controlautomatic controlSubject Category: Miscellaneous
    see more details
    , automationautomationSubject Category: Miscellaneous
    see more details
    , camerascamerasSubject Category: Techniques, Methodologies and Equipment
    see more details
    , graingrainSubject Category: Commodities and Products
    see more details
    , hoppershoppersSubject Category: Techniques, Methodologies and Equipment
    see more details
    , image analysisimage analysisSubject Category: Techniques, Methodologies and Equipment
    see more details
    , image processingimage processingSubject Category: Techniques, Methodologies and Equipment
    see more details
    , lightlightSubject Category: Miscellaneous
    see more details
    , machine visionmachine visionSubject Category: Techniques, Methodologies and Equipment
    see more details
    , prototypesprototypesSubject Category: Techniques, Methodologies and Equipment
    see more details
    , robotsrobotsSubject Category: Techniques, Methodologies and Equipment
    see more details
    , unloadersunloadersSubject Category: Techniques, Methodologies and Equipment
    see more details
    , unloadingunloadingSubject Category: Techniques, Methodologies and Equipment
    see more details
    , techniquestechniquesSubject Category: Techniques, Methodologies and Equipment
    see more details

    Identifier(s) : computer vision