MACHINE VISION SMART SPRAYER FOR SPOT-APPLICATION OF AGROCHEMICAL IN WILD BLUEBERRY FIELDS

Abstract. An essential part of the wild blueberry cropping system is the proper management of agrochemical inputs including herbicides, fungicides and insecticides. A machine vision system was developed and mounted on the rear sprayer boom in front of the sprayer nozzles capable of targeting the agrochemical application on an as-needed basis. The three-point hitch mounted sprayer featured 27 nozzles over a 13.7 m boom width and a storage tank capacity of 1135 L. Nine digital color cameras continually take images in real-time while custom software processes the images to determine the target locations where the nozzles open and spray. Wild blueberry fields in central Nova Scotia were used for the experiment. Data collection included; GPS coverage maps, target locations, and plant parameters (stem height, stem diameter, stem density, number of branches, number of fruit buds, and wild blueberry yield). Images were collected after fungicide application for comparison of the different application techniques. The images were visually classified into five categories (0 – complete leaf defoliation, 1 – partial leaf defoliation, 2 – no leaf defoliation (mostly red plants), 3 – no leaf defoliation (red/green plants), 4 – no leaf defoliation (mostly green plants) to determine plant healthiness. Results showed that plants that received the proper fungicide application were less prone to premature leaf drop resulting in larger stem diameters, higher bud counts and harvestable fruit yield. Fungicide application savings using the smart sprayer for spot-application ranged from 10 to 12.6 percent as compared to uniform applications.