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.

One of the main stages in the automatic guidance of agricultural vehicles is the detection of crop rows. The purpose of this paper is to present a machine vision algorithm to find the rows in a soybean field. A video camera was mounted on a tractor in order to capture real images, and send them to a computer for processing. The vision algorithm was based on the Hough transform and blob analysis techniques, and its outputs were the equations of the lines representing the rows. Between one and five lines were generally found to determine the desired trajectory. The information provided by these lines was effective to identify the path to be followed by the tractor. The algorithm overcame image noise problems.