Bare Spots Mapping in Wild Blueberry Fields using Digital Photography

Abstract

Wild blueberry is a unique crop native to Northeastern North America and fields are developed from native stands on deforested farmland by removing competing vegetation. The majority of fields are situated in naturally acidic soils that are low in nutrients and have high proportions of bare spots, weed patches and gentle to severe topography. This crop is perennial in nature, having a vegetative growth season (sprout year) followed by productive season (fruit year). Wild blueberry producers apply agrochemicals uniformly without considering bare spots. The unnecessary or over-application of agrochemicals may increase cost of production, deteriorate fruit quality and increase environmental pollution. The objective of this study was to develop machine vision technology to detect and map bare spots for site-specific application of agrochemicals within wild blueberry fields. The experiment was conducted at a 4.0 ha wild blueberry field in central Nova Scotia. An automated cost-effective vegetation mapping system comprising of digital color camera, DGPS, toughbook was developed and mounted on specialized farm vehicle. Custom software for grabbing and processing color image was developed. The color images were downloaded from the digital camera in a toughbook and then processed either in RGB or HSV color space to extract bare spots. The best result was obtained by Hue image with recognition ratio of 99% and processing speed of 661 milliseconds.