DescriptionIn fruit production reliable and accurate information is needed for optimal orchard management. Due to an increase in farm size and high labour input, a grower gets less information feedback from what is going on in the orchard. Besides that, more detailed information about the fruit production is needed later in the chain to meet consumer demands and regulation requirements. Therefore the goal in the Fruit 4.0 project is to get a better insight in apple production by gathering more data and improving data management. In order to improve current practices we aim to quantify the most important parameters used in decision making during the growth season: number of blossom clusters, fruit number and size (> 10 mm), shoot length, leaf vitality, leaf quantity and fruit colour. Throughout the growing season it is also a goal to measure tree parameters such as canopy volume, height and vitality. Sensors used for these purposes are a 2d-lidar system, a chlorophyll sensor and a RGB-d camera. Apple trees produce variable numbers of flowers per year, but in general high numbers, with a high variability. To get to an optimal number, chemical, mechanical or manual thinning is applied by the grower. To automate this process we are using RGB-d images taken throughout the flowering period and at fruitlet stage combined with different classification techniques to estimate the number of blossoms and fruitlets per tree, to apply tree-specific thinning in the future. At later stages of the growing season the number and size of fruits are determined to optimise yield estimations and the harvest time, so labour requirements can be better estimated and planned. The demonstrated multi-sensor setup gives better insight into the growing conditions of the trees in order to optimise crop protection application and management practices tree specifically.
|Period||11 Jul 2018|
|Event title||AgEng Conference 2018: New Engineering concepts for a valued agriculture|