Development of a robotic weed control device Project leader Jānis Jaško Team of project Niks Ozols Jevgenija Ņečajeva Viktorija Zagorska Duration 2019 - 2020 Research focus 4. Development and adaptation of technologies for obtaining high-value agricultural and forest products, as well as in veterinary medicine Source of funding National grant Project partners Institute of Electronics and Computer Science“Lejasvagaļu dārzs” Ltd.farm “Absolūts Ēd”farm “Atvases Description of project The aim of research To develop a weed control device that is able to move autonomously in the field, identify weeds and separate them from the crop, as well as destroy the weed or significantly interfere with its further growth using a high-energy laser or precisely positioned mechanical unit. The tasks of project: To prepare and label of a visual data set for weed recognition algorithm training that includes weed tracking, photo taking and electronic processing to identify crops and weeds by identifying their species, genus or higher taxonField testing of the developed equipment, at the end of which it must be ensured that the developed equipment is able to perform the tasks defined for it in the fieldTo organize 3 field days Results The most important publication: J. Jaško , (2020), Dataset of annotated food crops and weed images for robotic computer vision control, Data in Brief, ISSN 2352-3409
