The proposed online system distinguishes crop from weeds based on multi-spectal reflectance gathered with an imaging spectrograph. Under field conditions, up to 86% of the vegetation samples (80% of crop. 91% of weed) were recognized herbicide reductions of up to 90%. (C) 2001 Elsevier Science B.V. All rights reserved.
Feyaerts F., Van Gool L., ''Multi-spectral vision system for weed detection'', Pattern recognition letters, vol. 22, pp. 667-674, 2001, Elsevier Science B.V.