Accessibility navigation


Proof of concept of automated mapping of weeds in arable fields

Murdoch, A. J., De La Warr, P. N. and Pilgrim, R. A., (2010) Proof of concept of automated mapping of weeds in arable fields. Project Report. AHDB-HGCA, Stoneleigh, Warwickshire. pp61.

Full text not archived in this repository.

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

Official URL: http://www.hgca.com/cms_publications.output/2/2/Pu...

Abstract/Summary

The project investigated whether it would be possible to remove the main technical hindrance to precision application of herbicides to arable crops in the UK, namely creating geo-referenced weed maps for each field. The ultimate goal is an information system so that agronomists and farmers can plan precision weed control and create spraying maps. The project focussed on black-grass in wheat, but research was also carried out on barley and beans and on wild-oats, barren brome, rye-grass, cleavers and thistles which form stable patches in arable fields. Farmers may also make special efforts to control them. Using cameras mounted on farm machinery, the project explored the feasibility of automating the process of mapping black-grass in fields. Geo-referenced images were captured from June to December 2009, using sprayers, a tractor, combine harvesters and on foot. Cameras were mounted on the sprayer boom, on windows or on top of tractor and combine cabs and images were captured with a range of vibration levels and at speeds up to 20 km h-1. For acceptability to farmers, it was important that every image containing black-grass was classified as containing black-grass; false negatives are highly undesirable. The software algorithms recorded no false negatives in sample images analysed to date, although some black-grass heads were unclassified and there were also false positives. The density of black-grass heads per unit area estimated by machine vision increased as a linear function of the actual density with a mean detection rate of 47% of black-grass heads in sample images at T3 within a density range of 13 to 1230 heads m-2. A final part of the project was to create geo-referenced weed maps using software written in previous HGCA-funded projects and two examples show that geo-location by machine vision compares well with manually-mapped weed patches. The consortium therefore demonstrated for the first time the feasibility of using a GPS-linked computer-controlled camera system mounted on farm machinery (tractor, sprayer or combine) to geo-reference black-grass in winter wheat between black-grass head emergence and seed shedding.

Item Type:Report (Project Report)
Divisions:Life Sciences > School of Agriculture, Policy and Development > Department of Crop Science
ID Code:18322
Publisher:AHDB-HGCA

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation