Automated Assessment and Mapping of Grape Quality through Image-based Color Analysis

Abstract

The harvest operation for table-grapes and fresh market horticultural fruits is a large and expensive logistical challenge with the choice of harvest dates and locations playing a crucial role in determining the quality of the yield and in determining the efficiency and productivity gain of the entire operation. The choice of harvest dates and locations, particularly in red varieties, is planned based upon the development of the color of the grape clusters. The traditional process to evaluate the amount of ripe, fully-colored fruit is visual assessment, which is subjective and prone to errors. The number of locations where a grower will evaluate the fruit development is statistically insufficient given the size of commercial vineyards and the variability in the color development. Therefore, an automated approach for evaluating color development is desirable. In this paper, we use a vision-based system to collect images of the fruit zone in a vineyard. We then use color image analysis to grade and predict the color development of grape clusters in the vineyard. Using our approach we are able to generate spatial maps of the vineyard showing the current and predicted distribution of color development. Our imaging measurement system achieves R2 correlation values of 0.42-0.56 against human measurements. We our able to predict the color development to within 5{%} average absolute error of the imaging measurements. The prediction of spatial maps is important from the perspective of selective harvesting as it allows the precise targeting of productive zones during the harvest operation. To the best of our knowledge generation of these spatial maps that represent the current and predicted state of the color development of an entire vineyard block, before harvest and in high resolution, is a first of its kind.