In-field grape berries counting for yield estimation using dilated CNNs
This work addresses the need for low-cost, scalable product quality control in precision agriculture, specifically for grape growers, but it is incremental as it adapts existing methods to a new domain.
The researchers tackled the problem of accurate fruit yield estimation in agriculture by adapting deep learning algorithms for crowd counting to count grape berries from smartphone camera images, achieving a tool for precise yield estimation.
Digital technologies ignited a revolution in the agrifood domain known as precision agriculture: a main question for enabling precision agriculture at scale is if accurate product quality control can be made available at minimal cost, leveraging existing technologies and agronomists' skills. As a contribution along this direction we demonstrate a tool for accurate fruit yield estimation from smartphone cameras, by adapting Deep Learning algorithms originally developed for crowd counting.