Material other than grain and broken grain sensor for combine harvesters

摘要

In this research, a technique has been elaborated to obtain a maximal color contrast between the pure kernels and the MOG (Material other than grain) in a grain image. Hyper-spectral measurements have been done on grain samples. The analysis of the data led to a selection of some specific wavelength regions. LED's of these corresponding wavelengths were used into the sensor setup to take a sequence of images of a grain sample on the combine harvester. In the algorithm development, multivariate image analysis has been applied to combine the information in the different monochrome images to a virtual image that shows a maximal contrast between the pixels of pure kernels and the pixels of MOG.