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.

Using Structured Lighting and Shadow for Leaf Segmentation

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

Citation:  Paper number  RRV07142,  ASABE/CSBE North Central Intersectional Meeting. (doi: 10.13031/2013.24185) @2007
Authors:   Peter Neil Kennedy, Scott D Noble
Keywords:   plant segmentation, depth edges, edge detection, shadow

Leaves in arrangements of tomato and bean plants were segmented using an edge detection technique that used shadows from multiple, differently illuminated images to identify shadow edges and compared the results with those of a more conventional single image technique that identified intensity gradient edges. Images were taken in a 10 nm waveband centred at 766 nm and segmented by both techniques. Shadow edges produced segmentation percentages of 7% for bean and 18% for tomato for partially occluded leaves. Gradient edges segmented 12% for bean and 10% for tomato for partially occluded leaves. The results are poor when compared with existing work but the different modes of failure show potential for hybrid imaging techniques

(Download PDF)    (Export to EndNotes)