Journal of Computer Science

DEVELOPMENT OF A PROXIMAL MACHINE VISION SYSTEM FOR OFF-SEASON WEED MAPPING IN BROADACRE NO-TILLAGE FALLOWS

H. Liu, C. Saunders and S. H. Lee

DOI : 10.3844/jcssp.2013.1803.1821

Journal of Computer Science

Volume 9, Issue 12

Pages 1803-1821

Abstract

Weeds are among the most significant and costly environmental threats in Australian agriculture. Weeds compete with crop plants for moisture, nutrients and sunlight and can have a detrimental impact on crop yields and quality if uncontrolled. The distribution, size, density and species of the weeds are often heterogeneous in the cropping land. Instead of uniformly spray the same type of herbicide to the whole farm land, selective spray can reduce the herbicide usage therefore can reduce the serious problems of herbicide resistance, soil damage and food safety. This study describes a weed mapping method which could be used for broadacre no-tillage fallow weed management. The weed maps have the potential to be used as powerful herbicide prescription maps for spot spray. The weed mapping is realized by the machine vision technologies which including image acquisition, image stitching and photomosaic processing. The sampling points are continuous and the interpolation methods are used at the minimum levels. The experiment result shows that this weed mapping method can map weed under limited conditions.

Copyright

© 2013 H. Liu, C. Saunders and S. H. Lee. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.