Authors: Rosa Pia Devanna, Francesco Vicino, Simone Pietro Garofalo, Gaetano Alessandro Vivaldi, Simone Pascuzzi, Giulio Reina, Annalisa Milella
Abstract: Pomegranate (Punica granatum) fruit size estimation plays a crucial role in orchard man- agement decision-making, especially for fruit quality assessment and yield prediction. Currently, fruit sizing for pomegranates is performed manually using calipers to measure equatorial and polar diameters. These methods rely on human judgment for sample se- lection, they are labor-intensive, and prone to errors. In this work, a novel framework for automated on-tree detection and sizing of pomegranate fruits by a farmer robot equipped with a consumer-grade RGB-D sensing device is presented. The proposed system features a multi-stage transfer learning approach to segment fruits in RGB images. Segmentation results from each image are projected on the co-located depth image; then, a fruit clus- tering and modeling algorithm using visual and depth information is implemented for fruit size estimation. Field tests carried out in a commercial orchard are presented for 96 pomegranate fruit samples, showing that the proposed approach allows for accurate fruit size estimation with an average discrepancy with respect to caliper measures of about 1.0 cm on both the polar and equatorial diameter.
