Open image database for growing crops - a foundation for the digitilization of agriculture
|Coordinator||RISE Research Institutes of Sweden AB - SICS EAST SWEDISH ICT AB|
|Funding from Vinnova||SEK 7 788 400|
|Project duration||November 2018 - December 2020|
Purpose and goal
The project aims to create an open large image database through which machine learning & computer vision, can be find where a particular crop grows on a field as well as its health & status. The goal is an image database of various named crops & weeds. This can then be used as a basis for decision support systems that help the farmer decide when it is time to fight weed. The information could in the future be used for direct control of measures to be taken, or to determine the proportion of different grass and clover species found in a field, which yields how to fertilize in order to maintain the clover.
Expected results and effects
The collected data will be published for free use. RISE thereby strengthens basic research on automatic recognition of crops relevant to Swedish conditions and its diseases, as well as creating new opportunities for start-ups to develop innovations in this area without taking the cost of data collection. Preliminary analyzes will provide indications of results that could be achieved in future applications. These can serve as a first input to environmental conservation authorities about what is possible with new technology, and thus provide the basis for any future legislation.
Planned approach and implementation
The project will use Testbed Digitalized Farming, which is run by RISE Jordbrug in Uppsala, to both develop collection methods & systems as well as to continuously collect images during all growth phases from seed to harvest using flying and ground-based camera systems. The use of two different collection systems is motivated by the fact that different views of the plant may be needed in future applications, and today it is not known which will be successful, but we want to provide the opportunity for both to be investigated. During the second year of the project, Testbed UAV will also be used.