Research objectives Use hyperspectral data from UAV platform for crop/weed discrimination Generation of spraying task /application maps for SSWM and validation The research will focus on two kind of weeds i.e. thistles in grassland and bindweeds in maize fields for case study. Field aerial hyperspectral images of thistles will be collected at the different growth stages and different flight height. The aerial images of bindweeds will also be taken in the early growth stage in the maize fields.

Information about the weed population in fields is important for determining the optimal herbicides for the fields. A system based on images is presented that can provide support in determining the species and density of the weeds. Firstly, plants are segmented from the soil. Plants that after the segmentation are divided in multiple parts are selected manually and a cost image is created by weighting pixels according to their relationship to plant. This relationship is based on the colours of pixels and the weighting of nearby pixels.

Development of vision technologi for detection of weeds in early development stage. Implementation in a weeding robot with thermal destruction of weeds. Suitable for production of organic food.

Precision agriculture for the sustainable management of weed. Aim of the project is to design and assess the effectiveness of a management system for synthetic herbycides using precision agriculture technologies. By means of recent innovations in electronics for machine control, remote sensing, and GPS what is to be proofed is the possibility to remarkably reduce the quantity of herbicides and increasing the treatment efficiency.

Automated Weeder Separates Friend from Foe. Friday, February 20, 2015 New technology being developed by the University of California – Davis is putting precision weed control onto farm equipment, which will eliminate the need for much of today’s manual labor. This is not your granddad’s weed whacker.

Broad-leaved dock (Rumex obtusifolius L.) is a common and troublesome weed with a wide geographic distribution. The weed is readily consumed by livestock but its nutritive value is less than that of grass. The high contents of oxalic acid and oxalates can affect animal health if consumed in larger doses. When left uncontrolled, the weed will reach a high density and reduce grass yield by 10 to 40%. In conventional dairy farming, the weed is normally controlled by using herbicides. In organic farming no synthetic pesticides are used and there is a risk that broad-leaved dock will spread.

In response to potential loss of herbicides due to EU Directives and regulations and other environmental pressures, the project is carrying out basic and applied research to facilitate the adoption of targeted patch spraying of grass weeds and selected broad leaved weeds in arable fields in the UK. Machinery and systems are already available for patch spraying. The barrier to adoption is knowing where the patches are located with the precision required.

The project will develop an autonomous robot allowing >50 % herbicide reduction in sugar beet weeding. New weed detection vision algorithms will be developed and ported to a graphics processing unit. A low-power robotic arm and robust multi-sensor navigation will be designed. Five solar-powered prototypes will be validated in real operation. The robot will significantly reduce weeding cost, allowing return on investment in 3 years. The project is aimed at distributing the robot in all of Europe, with envisaged sales of 1000 robots per year from 2018 on.

This project is funded by the innovation program of the Federal Ministry of Food and Agriculture (BMEL), funding agency is the Federal Office for Agriculture and Food (BLE). Remote sensing of weed infestations For an improved weed control which is adapted to the current situation in the field, the farmer needs information about the weed infestation to specifically adjust the management of weed control. In the project REMWEED tools are developed to determine the weed infestation spatially.