Precisietechnologie Tuinbouw: PPS Autonoom onkruid verwijderen: D2.4 Literatuurstudie spectrale reflectie-eigenschappen van planten en onkruiden; D2.5 Lab en veldexperimenten spectrale reflectie-eigenschappen van planten en onkruiden

This report contains the two deliverables of the research project “autonomous weed removal” that deal with the topic hyper- and multispectral weed detection. In the literature of the past 10 to 15 years, there are sufficient indications that a good distinction on the basis of spectral characteristics can be made between various plant species. For the hyperspectral lab measurements, various crops and weeds have been cultivated. The reflection spectrum of all plants was measured between 400 and 1000 nm and between 900 and 1700 nm on different growing stages in the laboratory. In particular the reflection in the chlorophyll range (650-670 nm) and in the green range (around 550 nm), red-edge (700 nm) and near-infrared (800 nm) show a distinctive power between the crops and weeds studied. With field measurements it was investigated whether it is possible to detect green weeds in a green lettuce crop using hyperspectral camera images. The accuracy of a correct classification on both measurement days was 6.9% and 9.9%, respectively, below the previously set target value of 90%. In order to exclude the effect of the use of different cameras on the test result, a comparative follow-up study is recommended.