Real-time Application of Herbicides in Seed Lines by Computer Vision and Micro-Spray System
H.T. Søgaard, Ivar Lund, Enrico Graglia
- Year
- 2006
- Citations
- 8
Abstract
Droplet application of herbicides at single weed seedlings was studied. Manual applicationof the droplets showed that 1 g per plant gave 95% efficacy. Assuming a weed density of 100 plantsm-2 this result corresponds to a glyphosate consumption of only 1 g ha-1. Automatic application ofherbicide droplets was performed with a vision controlled micro-spray system installed in anautonomous robot. Under indoor conditions it was demonstrated that objects which were the size ofa weed seedling could be hit at sub-centimeter accuracy. Only about 10 L of spray liquid was usedper object which corresponds to a few g of glyphosate. In an outdoor field experiment with theautomatic micro-spray system efficacies of 82% were obtained with 22.6 g of glyphosate per planton average. This is only around 4% of the official label recommendation for glyphosate.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002