Using AI, computer vision, and robotics to predict tomato plants growth
Auf einen Blick
Crops growth management in greenhouses is fundamental for their economical and ecological sustainability. Typically, smaller size greenhouses have the challenge to grow more than one crop variety, each having different growth control strategies. A precise estimate of the expected harvest and crop balance allows greenhouse managers to preventively sell crops on the market while minimizing the risk of overselling and waste. Moreover, being able to monitor the crop balance and plant load of all different varieties in the greenhouse, the grower can take measures to control crop growth in a way to reduce fluctuations that would require constantly adjusting the workforce for all required tasks (e.g., harvesting, leaf thinning, plant rotation).
Crop growth prediction is currently performed manually, collecting data from sampled plants (e.g., measuring stems, counting flowers and fruits), which is expensive, time consuming, and only gives a sample representation of the greenhouse. Precision agriculture (e.g., depth and spectral cameras, AI, robots) can provide an inexpensive and effective solution to collect data. A data-driven approach to greenhouse growth management would benefit all producers, optimize production, and reduce waste across entire markets.