Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Three dimensional mapping of Citrus Fruits in the canopy using computer vision

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2011 Louisville, Kentucky, August 7-10, 2011  1110719.(doi:10.13031/2013.43918)
Authors:   Venkat Jayaraman, Thomas F Burks, Jeffrey Ho, Duke M Bulanon
Keywords:   Image processing, three dimensional maps, robotic citrus harvesting

The development of three dimensional maps of citrus fruits in the canopy has the potential in increasing the harvest efficiency for robotic fruit harvesting. In this paper, two methods have been developed and compared for their effectiveness in estimating the three dimensional map of the citrus fruits in the canopy. The first method, which uses one camera, estimates the 3D position of the fruit using the statistical size of the fruit. The depth of the fruit is calculated as a function of perimeter of the fruit in the image and the fruits average size. The second method based on stereo vision uses a two camera system to estimate the three dimensional position of the citrus fruits in the canopy. The 3D position estimation performances of both methods were evaluated by conducting three different experiments and their results have been presented.

(Download PDF)    (Export to EndNotes)