Development of an Automatic System to Detect and Spray Herbicides in Corn Fields

Abstract

Weed control is vital in agricultural production. Chemical controlmethods are generally preferred in weed control as they (1) affectquickly and (2) reduce the labour requirement. However, inconventional applications chemicals are generally applied towhole field surface. Therefore, non-targeted areas are alsosprayed. This increases 1) amount of herbicide used and (2)risk of off-target chemical movement. In this study, a patchspraying system was developed to automatically detect and sprayherbicides on weeds in the corn field based on weed density. Inorder to determine the weed regions, a digital camera was fittedin front of the tractor. The images taken using the camera werethen simultaneously processed using an algorithm written inMatlabTM software. The results of the field study showed that at4, 6 and 8 km h-1 forward speeds, application volumes decreaseby 30.21%, 28.82% and 32.28%, respectively, when it iscompared to the conventional application methods. It was alsodetermined that the application accuracy rates were 80%, 81.66%and 75% respectively for 4, 6 and 8 km h-1 speeds.