Development of a prototype precision spot spray system using image analysis and plant identification technology

Abstract

A project funded by the Australian Sugar Research and Development Corporation aimed to increase sugarcane production through cost effective automated precision weed spraying. The project developed a precision imaging system that could be integrated with current spraying systems to specifically target difficult to control weeds such as guinea grass/green panic. The technology is capable of differentiating weeds from sugarcane in the row area and actuating a spray solenoid so that only the weeds are sprayed with herbicide in a single pass and with minimal over-spraying of the crop. The precision imaging and spot spraying technology demonstrated proof-of-concept and a cost benefit analysis of the new weed control system indicated potential grower savings. This paper will report on a review of appropriate technologies, description of the prototype sugarcane image analysis system and algorithms, assessment of accuracy of weed identification and an evaluation of system costs and performance.