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.

Ground based vision identification for weed mapping using DGPS

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

Citation:  Paper number  031005,  2003 ASAE Annual Meeting . (doi: 10.13031/2013.15382)
Authors:   D. Downey, D.K. Giles, D.C. Slaughter
Keywords:   DGPS, weed location mapping, recurrent weeds, video image capture

An automatic weed mapping location and identification system is described using cotton as the target crop. Field boundaries were mapped with a conventional DGPS data logging device. The system used a 3-CCD camera for capturing images along the seedline while concurrently capturing data from the GPS receiver. Images were synchronized with GPS time in order to overlay GPS coordinates onto select images during post processing of data. A computer program was written that used GPS time and frame count of the video feed to overlay the coordinates on representative images for specific locations. The video camera continuously mapped nutshedge weeds and crop plants within the seedline. The methods and procedures described can give locations of weeds with centimeter scale accuracy when RTK-GPS is used. This work may be used for future development of database themes and features that could be an add-on to commercially available software.

(Download PDF)    (Export to EndNotes)