Machine learning, neural and statistical classification
Machine learning, neural and statistical classification
Multi-spectral vision system for weed detection
Pattern Recognition Letters
Weed detection in multi-spectral images of cotton fields
Computers and Electronics in Agriculture
Computers and Electronics in Agriculture
Improving in-row weed detection in multispectral stereoscopic images
Computers and Electronics in Agriculture
Analysis of natural images processing for the extraction of agricultural elements
Image and Vision Computing
Computers and Electronics in Agriculture
Spatially discriminating Russian wheat aphid induced plant stress from other wheat stressing factors
Computers and Electronics in Agriculture
Hi-index | 0.00 |
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 700nm. 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.