AN ALGORITHM FOR SEPARATING GUIDANCE INFORMATION FROM ROW CROP IMAGES Academic Article uri icon

abstract

  • A statistical-based algorithm was developed for selecting a threshold to segment row crop images into classes of information corresponding to the crop canopy and soil background. Systematic image sampling was used to determine an estimate of the population of pixels in an image. An automatic-iris lens and an optical filter were used to enhance image contrast to minimize computational image processing requirements. The threshold was selected using a Bayes classifier. The two image intensity classes were assumed to be independent Gaussian random variables. The distribution parameters used in classification were estimated using the method of moments. Data are presented on the development and performance of the thresholding algorithm on 16 representative row crop images. The algorithm was an effective classification technique for segmenting row crop images into crop canopy and soil background classes. The segmented row crop images will need to undergo additional processing to determine the location of the rows and the tractor guidance signal.

published proceedings

  • TRANSACTIONS OF THE ASAE

author list (cited authors)

  • REID, J. F., & SEARCY, S. W.

complete list of authors

  • REID, JF||SEARCY, SW

publication date

  • November 1988