Every year a large amount of greenhouse-grown food goes to waste because of non-optimized yield planning, logistics, etc. Tomatoes are one of the most consumed vegetables both in the EU and worldwide, and it is estimated that around 3 mill. tonnes of tomatoes are wasted in the EU annually. This leads to inefficient use of resources and economic loss.​

Greenhouses frequently encounter significant challenges with overproduction and food loss due to mismatches between supply and fluctuating demand. Sudden shifts in market demand can result in surplus produce that exceeds consumption needs, leading to wasted resources. Diseases and mechanical damage lower the quality of some fruit, contributing further to waste. Inefficient harvest planning and timing only worsen these issues, causing unnecessary food loss and financial setbacks.

To tackle these challenges, a precise monitoring system that helps forecast yields accurately and align production with market demands is crucial and could help reduce food loss and waste.

Computer-vision based systems to monitor growing vegetables 

In this project, we are developing an advanced monitoring system to assist farmers in harvest planning and work optimization using computer vision and artificial intelligence.

This system employs multiple cameras to capture images of tomatoes, which are then processed by specialized custom analysis software. This software features machine-learning models designed to identify and count tomato fruits, assess their ripeness, and estimate their weight from the images alone.

The software predicts future tomato yields based on this visual data analysis. Farmers can access these insights via an interactive online dashboard, enabling more informed decision-making and efficient harvest management.