Method and apparatus for the optical evaluation of harvested crop in a harvesting machine

摘要

An arrangement for the optical evaluation of harvested crop in a harvesting machine includes a camera located for taking images of threshed out crop elements (grain and material other than grain) being conveyed within a channel of the machine. An electronic image processing system receives the images and identifies individual objects in the images, these objects being classified into predetermined object classes by way of comparing at least one of color, contour or texture features of the individual objects and corresponding characteristics of reference objects filed in a data bank. The processing system then determines the absolute or relative numbers or areas of the individual objects assigned to the respective object classes.

主权项

1. A method for the optical evaluation of harvested crop, said method including the following steps:
a) recording an image of the harvested crop (62) in a channel (50) within a harvesting machine (10) with a camera (66); b) identifying individual objects in the image by means of an electronic image processing system (80) by dividing the image into individual objects and background by means of a binary cutting mask; c) processing further the individual objects in a size-dependent manner, wherein:
i) individual objects having at least one dimension below a threshold value being treated as background,ii) and individual objects having at least one dimension above a threshold value being divided up into several individual objects by local brightness scaling and an application of the cutting mask with sharper discrimination parameters than during the first application of the cutting mask in step b)iii) and the center of gravity and the respective orientations of the individual objects are inspected and the point clouds of two individual objects are merged if the center of gravity of another single object is in the vicinity of a region currently to be inspected and the respective orientations are similar; d) classifying, by means of the image processing system (80), the individual objects into predetermined object classes by way of comparison between characteristics of the individual objects and characteristics of reference objects filed in a data bank (78), wherein the characteristics of the individual objects compared during classification include at least one of color features, contour features and texture features of the individual objects; and e) determining the absolute or relative numbers or areas of the individual objects assigned to the respective object classes.