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.

Early Growth Stage Corn Plant Population Measurement Using Neural Network Approach

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

Citation:  Pp. 8-14 in Proceedings of the World Congress of Computers in Agriculture and Natural Resources (13-15, March 2002, Iguacu Falls, Brazil)  701P0301.(doi:10.13031/2013.8305)
Authors:   D.S. Shrestha and B.L. Steward
Keywords:   Plant population, machine vision, neural network, segmentation

A major cause of corn yield variation within a field is plant population variation. An early plant population sensing system has potential as a tool for evaluating spatially varying emergence patterns and planter performance. Machine vision technology for automatically sensing early growth stage corn plant density and spacing was devel-oped in this research. Correspondence between sequential field images taken from a digital video camera was determined using pattern matching of intensity images. A color segmentation algorithm was used to separate plants from background. A neural network (NN) approach was used to correlate the green region in RGB color space to different lighting conditions. Plants were singulated based on plant object shapes. The NN approach was effective in adjusting the segmentation decision surface based on general measures of lighting changes.

(Download PDF)    (Export to EndNotes)