Multispectral image labeling using radiometric attribute vectors of image space representation components

摘要

Automatic characterization or classification of a portion of an input multispectral image based on a selected reference multispectral image. The set of radiometric descriptors (eg, vectors) for each component pixel in the hierarchical representation of the input multispectral image can be collectively manipulated to obtain a set of radiometric descriptors for that component. Each component is obtained by comparing (eg, mining material, crops, etc.) of at least one reference multispectral image (eg, mine material, crop, etc.) through a comparison of the set of component radiometric descriptors and the set of radiometric descriptors for the reference multispectral image. (Relative) can be labeled as positive or negative cases. A pixel may be labeled (eg, by color, pattern, etc.) as a positive or negative case of the land use or land type of the reference multispectral image in the resulting image based on the component in which the pixel is found.