Overview
In order to develop AI applications or vision functionalities in robots, one of the first steps is to have high-quality images of crops, weeds, nutrient deficiencies, diseases, or pests available. As the phenotype of plants can really differ between regions and seasons, providing balanced datasets with high-quality images and different illumination could save valuable (development and acquisition) time. The data can be used for annotation purposes or to have a first visual check if an existing trained algorithm works sufficiently.
More about the service
How can the service help you?
The customer can use the data for annotation purposes, first tests of an algorithm, and get a feeling of the variety to deal with.
How the service will be delivered
In personal contact with the customer, we identify which data and requirements are needed. Next we'll identify if there are datasets available within WR or if new data has to be acquired. We've got all kinds of equipment and the facilities available to start new data acquisition in several locations throughout the Netherlands. We'll provide the data through a portal (in development).
Service customisation
Depending on the use case and wishes of the customer, we have equipment and test fields throughout the Netherlands (different soils and crop conditions) available to acquire new data. This can also be other types of sensors that are comparable with the sensors the customers use.
Sector
Arable farming
Horticulture
Tree Crops
Test type
Data
Software or AI model
Type of service
Collection of test data
Provision of datasets
Country of delivery
Country of delivery:
Service provider(s):
-
Wageningen University WUR
| Website
