Share Email Print
cover

Proceedings Paper

Combining spatial and spectral information to improve crop/weed discrimination algorithms
Author(s): L. Yan; G. Jones; S. Villette; J. N. Paoli; C. Gée
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Reduction of herbicide spraying is an important key to environmentally and economically improve weed management. To achieve this, remote sensors such as imaging systems are commonly used to detect weed plants. We developed spatial algorithms that detect the crop rows to discriminate crop from weeds. These algorithms have been thoroughly tested and provide robust and accurate results without learning process but their detection is limited to inter-row areas. Crop/Weed discrimination using spectral information is able to detect intra-row weeds but generally needs a prior learning process. We propose a method based on spatial and spectral information to enhance the discrimination and overcome the limitations of both algorithms. The classification from the spatial algorithm is used to build the training set for the spectral discrimination method. With this approach we are able to improve the range of weed detection in the entire field (inter and intra-row). To test the efficiency of these algorithms, a relevant database of virtual images issued from SimAField model has been used and combined to LOPEX93 spectral database. The developed method based is evaluated and compared with the initial method in this paper and shows an important enhancement from 86% of weed detection to more than 95%.

Paper Details

Date Published: 2 February 2012
PDF: 8 pages
Proc. SPIE 8300, Image Processing: Machine Vision Applications V, 83000E (2 February 2012); doi: 10.1117/12.909861
Show Author Affiliations
L. Yan, AgroSup Dijon (France)
G. Jones, AgroSup Dijon (France)
S. Villette, AgroSup Dijon (France)
J. N. Paoli, AgroSup Dijon (France)
C. Gée, AgroSup Dijon (France)


Published in SPIE Proceedings Vol. 8300:
Image Processing: Machine Vision Applications V
Philip R. Bingham; Edmund Y. Lam, Editor(s)

© SPIE. Terms of Use
Back to Top