[en] The aim of this study was to select the best combination of filters for detecting various weed species located within carrot rows. In-field images were taken under artificial lighting with a multispectral device consisting of a black and white camera coupled with a rotating wheel holding 22 interference filters in the VIS-NIR domain. Measurements were performed over a period of 19 days, starting 1 week after crop emergence (early weeding can increase yields) and seven different weeds species were considered. The selection of the best filter combination was based on a quadratic discriminant analysis. The best combination of filters included three interference filters, respectively centred on 450, 550 and 700 nm. With this combination, the overall classification accuracy (CA) was 72%. When using only two filters, a slight degradation of the CA was noticed. When the classification results were reported on field images, a systematic misclassification of carrot cotyledons appears. Better results were obtained with a more advanced growth stage. (c) 2007 Elsevier B.V. All rights reserved.
Aitkenhead M.J., Dalgetty I.A., Mullins C.E., McDonald A.J., and Strachan N.J. Weed and crop discrimination using image analysis and artificial intelligence methods. Comput. Electron. Agric. 39 (2003) 157-171
Alchanatis V., Ridel L., Hetzroni A., and Yaroslavsky L. Weed detection in multi-spectral images of cotton fields. Comput. Electron. Agric. 47 (2005) 243-260
Borregaard T., Nielsen H., Norgaard L., and Have H. Crop-weed discrimination by line imaging spectroscopy. J. Agric. Eng. Res. 75 (2000) 389-400
Dagnelie, P., Statistique théorique et appliquée 2-Inférence statistique à une et à deux dimensions. De Boeck ed., Bruxelles, 2006.
Daughtry C.S.T., and Biehl L.L. Changes in spectral properties of detached birch leaves. Remote Sens. Environ. 17 (1985) 281-289
El-Faki M.S., Zhang N., and Peterson D.E. Weed detection using color machine vision. Trans. ASAE 43 6 (2000) 1969-1978
Feyaerts F., and Van Gool L. Multi-spectral vision system for weed detection. Pattern Recogn. Lett. 22 (2001) 667-674
Franz E., Gebhardt M.R., and Unklesbay K. The use of local spectral properties of leaves as an aid for identifying weed seedlings in digital images. Trans. ASAE 34 2 (1991) 682-687
Gee, C., Bonvarlet, L., Magnin-Robert, J.B., Guillemin, J.P., 2004. Weed discrimination by reflectance measurements using neural networks. In: Douzième Colloque international sur la biologie des mauvaises herbes, Dijon, France, Paris: AFPP.
Goel P.K., Prasher S.O., Patel R.M., Landry J.A., Bonnell R.B., and Viau A.A. Classification of hyperspectral data by decision trees and artificial neural networks to identify weed stress and nitrogen status of corn. Comput. Electron. Agric. 39 (2003) 67-93
Hemming J., and Rath T. Computer-vision-based weed identification under field conditions using controlled lighting. J. Agric. Eng. Res. 78 3 (2001) 233-243
Hunt E., Raymond Jr., McMurtry, James III E., Parker Williams, Amy E., Corp, and Lawrence A. Spectral characteristics of leafy spurge (Euphorbia esula) leaves and flower bracts. Weed Sci. 52 (2004) 492-497
Kleynen O., Leemans V., and Destain M.-F. Selection of the most efficient wavelength bands for 'Jonagold' apple sorting. Posthar. Biol. Technol. 30 (2003) 221-232
In: Michie D., Spiegelhalter D.J., and Taylor C.C. (Eds). Machine Learning, Neural and Statistical Classification (1994), Ellis Horwood, Chichester, UK
Noble, S.D., Crowe, T.G., 2001. Background Effects on Apparent Leaf Reflectance. ASAE Technical Library Paper no. 01-1177, ASAE, St. Joseph, MI, USA.
Noble, S.D., Brown, R.B., Crowe, T.G., 2002. The use of spectral properties for weed detection and identification-a review. In Canadian Society of Agricultural Engineers, Saskatoon, SK. 14-17 July 2002. CSAE Paper 02-208. CSAE/SCGR, Mansonville, QC, Canada.
Onyango C.M., and Marchant J.A. Segmentation of row crop plants from weeds using colour and morphology. Comput. Electron. Agric. 39 (2003) 141-155
Perez A., Lopez F., Benlloch J.V., and Christensen S. Colour and shape analysis techniques for weed detection in cereal fields. Comput. Electron. Agric. 25 (2000) 197-212
Tillett, Nick D., Hague T., and Miles S.J. A field assessment of a potential method for weed and crop mapping on the basis of crop planting geometry. Comput. Electron. Agric. 32 (2001) 229-246
Turner R. J., Davies G., 2005. Weed management in organic carrots, HDRA no. 298104.
Turner R.J., and Grundy A.C. Weed control strategies in organically grown carrots UK Organic Research 2002. In: Powell, et al. (Ed). Proceedings of the COR Conference. Aberystwyth (2002) 229-230
Vrindts E., De Baerdemaeker J., and Ramon H. Weed detection using canopy reflection. Precis. Agric. 3 (2002) 63-80
Wang N., Zhang N., Dowell F.E.Y.S., and Peterson D.E. Design of an optical weed sensor using plant spectral characteristics. Trans. ASAE 44 2 (2001) 409-419
Zhang N., and Chaisattapagon C. Effective criteria for weed identification in wheat fields using machine vision. Trans. ASAE 38 (1995) 965-974
Zhao D.H., Li J.L., and Qi J.G. Identification of red and NIR spectral regions and vegetative indices for discrimination of cotton nitrogen stress and growth stage. Comput. Electron. Agric. 48 (2005) 155-169