Deploying Deep Neural Networks on Edge Devices for Grape Segmentation

Abstract

Deep learning (DL) is a hot trend for object detection and segmentation, thanks to the use of Deep Neural Networks (DNNs). Image recognition is a powerful tool for precision viticulture, having a strong potential in cases such as yield estimation and automatic quality estimation of the grapes. Developing the models is one part of the problem, deploying them in the field, at the edge of the network, is another problem that comes with its own constraints. This paper studies the use of embedded devices to run Deep Neural Network algorithms for real-time grape segmentation at the wine press.