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.

DEVELOPMENT OF LASER CROP ROW SENSOR FOR AUTOMATIC GUIDANCE SYSTEM OF IMPLEMENTS

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

Citation:  Automation Technology for Off-Road Equipment,Proceedings of the 7-8 October 2004 Conference (Kyoto, Japan)Publication Date 7 October 2004  701P1004.(doi:10.13031/2013.17826)
Authors:   T. Satow, K. Matsuda, S. B. Ming, K. Hironaka, D. L. S. Tan
Keywords:   Laser distance sensor, Polygon mirror, Crop row sensor, Row crop tracking

In many farm operations, implements must follow the rows of the crops. Doing this, the tractor operator must frequently looks back, twisting his body while checking the work being done. This is not only difficult, but also prone to errors. To improve this system and obtain labor savings, a study of an automatic crop row guidance system for use in tractor mounted implement was conducted. Specifically, a laser crop row sensor, which is the most important part of the guidance system, was developed. The sensor applied a three-dimensional vision sensor, consisting of a laser distance sensor, polygon mirror, electric motor and computer. It can measure the height of the crop rows through the computer and the rotating mirror, which detects the crop row position or tracking line marker drawn on the surface of the soil by a seeder. When mounted at a height of 250 - 350 mm from the surface, the sensor can measure the horizontal position of the surface objects 150 mm to either sides of the center position. A high degree of linearity was obtained between the object positions and the actual measurement values of the sensor, with a correlation coefficient of 0.999 or more within 80mm. With the sensor mounted in front of the tractor, and using the model row crop and the tracking line marker, the sensor was able to measure the position of model crops and lines within 10 mm error, which makes this system reliable as a crop row sensor.

(Download PDF)    (Export to EndNotes)