Protected cultivations are expanding all over the world. However, protected cultivation involves the intensive use of resources such as soil, water, fertilizers, pesticides and energy. As a consequence, such intensive production systems are perceived by many as artificial and highly pollutant processes. Protected cultivation, and more particularly greenhouse production, has to be more respectful to the environment. The greenhouse of the future will have nearly zero environmental impact. This goal can be achieved by developing a sustainable greenhouse system.
The greenhouse climate can be optimised based on measurements of the plants instead of measuring its environment. That way safety margins growers normally take into account can be smaller, resulting in savings of water and energy.
One of the key polluting factors is the use of plant protective chemicals. Use of these chemicals can be reduced when diseases can be detected in an early stage. To reduce the use of resources, either water, energy and pesticides, this project aims to develop automated non-destructive quality assessment by measuring crop quality. To improve the usability of the technologies, we focus on flexible systems that can learn detection of new quality aspects and plant diseased from a number of examples.
This project has the aim to reduce resource spoilage by developing autonomous and flexible quality-assessment systems. Using state-of-the-art technologies in machine learning, we will develop methods that learn to translate raw sensor information into quality aspects of greenhouse crops. The system can be trained from a number of examples, which can be presented to the system by the crop expert. We will focus on four types of sensor data; NIR spectra, RGB images, RGB-D (depth) images and hyperspectral images. The first holds spectral information, the second and third spatial and 3D information and the fourth spectral and spatial information combined. The developed methods will be tested on a number of case studies; detection of thrips in chrysanthemum, detection of botrytis in cyclamen, detection of powdery mildew in tomato en chrysanthemum, as well as common quality features in tomato crops.