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.

Study on Fruit Visibility for Robotic Harvesting

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

Citation:  2007 ASAE Annual Meeting  073124.(doi:10.13031/2013.23428)
Authors:   D M Bulanon, T F Burks, V Alchanatis
Keywords:   Citrus, image processing, machine vision, robotic harvesting

One of the major challenges in developing a machine vision system for robotic fruit harvesting is fruit visibility. Fruit trees such as oranges have a dense canopy, which can often result in partial or complete occlusion. This paper discusses improved visibility of oranges using multiple viewing angles. Fruit visibility was defined as the ratio of the number of fruits recognized in the image to the total number of fruits inside the region of interest, which was a section of tree canopy enclosed by a bounding box. Multiple images of the region of interest from different viewing angles were acquired and analyzed. Results from both manual and automatic recognition approaches showed 90% and 87% fruit visibility respectively. These levels are a significant improvement over earlier reports in literature which ranged from 65 to 80%.

(Download PDF)    (Export to EndNotes)