The U.S. is the world’s largest producer of cranberry (Vaccinium macrocarpon Aiton). Cranberry fruit rot is the most prevalent disease problem for the cranberry industry, causing crop losses of more than 50%. The most common control measure relies on fungicide treatments. The recent withdrawal of common and effective fungicides used to treat cranberry fruit rot has moved the cranberry industry to search for alternative fungicides less harmful to human and environmental health. We are testing 15 different fungicide regimes, applied at three bloom periods (early bloom, mid-bloom, and late bloom), in randomized block trial in a bog of a single cranberry cultivar (Stevens) at the Cranberry Extension Station of University of Massachusetts. Our main goal is to determine the effect of the different fungicide treatments on fruit rot and fruit quality parameters for defining the best regime and timing of application. A secondary goal is to determine if high-throughput imaging can be used to phenotype fruit rot and fruit quality. We acquired images (one every second) using a handheld gimbal-mounted sensor system, the Sequoia Parrot+, which combines light sensors, GPS, an RGB camera, and four narrow-band sensors in the green, red, red edge, and NIR spectra. Using plot-level images extracted from an orthomosaic in each spectrum, we will explore image-analysis strategies for measuring yield, fruit quality, and fruit rot infection, and compare to values obtained by classic manual phenotyping (harvesting all berries in a 12-inch square section in the center of each plot). We will use these comparisons to define and improve the accuracy of high-throughput phenotyping as a new tool for monitoring fruit rot disease in the field for both research and commercial purposes.