Garford Farm Machinery has introduced a new generation of vision guidance system for its Robocrop precision weeders.
Developed in-house, Robocrop AI is said to deliver higher uptime, increased capacity and a reduced cost of operation. Capable of green on green plant recognition, the system combines colour, infrared and depth information to identify crop plants and stem location.
“Green on green plant recognition is a step change from the green on brown system that uses colour only. This new system uses multiple different data streams from the camera, and is able to then identify crop plants and distinguish those from weeds or non-crop plants,” explains Garford Farm Machinery managing director Jonathan Henry.
He adds that the ability to accurately locate the stem of the crop means that the hoeing elements can be guided closer to the plant, even when leaves are overlapping. This leads to a greater level of weed control.
The new camera system also enables the machine to work even in low light levels, or during cloud cover. Combined with an AI neural network, the system can distinguish plants from weeds based on colour, leaf shape and profile.
“Using multiple data streams means that, if for example due to weather conditions the operator is going out late and the weed pressure has intensified, you can still identify the crop plants and hoe with high precision,” Jonathan says.
The new system will be available on 2025 InRow electric rotor weeders, capable of working in salad, brassica and sugar beet crops. The first models will be available with single-section steering, and either single or double camera configurations.
In the cabin, a 10.1in terminal with a newly developed interface enables operators to livestream images from the field and adjust the sideshift.
For more information go to www.garford.com