论文信息 - Multi-spectral vision system for weed detection

Multi-spectral vision system for weed detection

Abstract 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%.

Luc Van Gool | F. Feyaerts | L. Gool | F. Feyaerts

[1] E. B. Knipling. Physical and physiological basis for the reflectance of visible and near-infrared radiation from vegetation , 1970 .

[2] David E. Battey,et al. Compact holographic imaging spectrograph for process control applications , 1993, Other Conferences.

[3] Luc Van Gool,et al. Weed detection based on structural information using an imaging spectrograph , 1998 .

[4] Keinosuke Fukunaga,et al. Introduction to Statistical Pattern Recognition , 1972 .

[5] M. R. Gebhardt,et al. Algorithms for Extracting Leaf Boundary Information from Digital Images of Plant Foliage , 1995 .

[6] P. Thornton,et al. Spatial weed distribution and economic thresholds for weed control , 1990 .

[7] W. Kühbauch,et al. Automatische Erkennung von zehn Unkrautarten mit Hilfe digitaler Bildverarbeitung und Fouriertransformation , 1993 .

[8] Esko Herrala,et al. Imaging spectrometer for process industry applications , 1994, Other Conferences.

[9] R. J. Haggar,et al. A prototype hand-held patch sprayer for killing weeds, activated by spectral differences in crop/weed canopies , 1983 .

[10] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .