The use of Site Specific Weed Management (SSWM) is increasing on European agriculture. It can be achieved by applying a treatment only to the weed patches by dividing the sprayer boom into independent sections. The majority of the implements use their own software and communication protocols, which hinders a wide adoption. Current tractors with the aid of ISOBUS can already achieve a certain level of site specificity. The DACWEED project is an EIT-Food project that will implement and combine novel components that already exist on the market: machine vision techniques, ISOBUS communication, and smart sprayers. Sensor data deriving from cameras will provide the input to a Neural Network in order to:
- separate the crop from weeds
- make decisions for herbicide spraying
- communicate actions through the ISOBUS to the relevant implements or tractor movements.
The integration of perception systems for the detection and control of action devices will allow a more exhaustive, and therefore effective, herbicide treatment. The herbicide input will be reduced, leading to safer agricultural products for the consumer and the environment, and ensure a more sustainable agriculture.