A new approach for the morphological segmentation of high-resolution satellite imagery

A new segmentation method based on the morphological characteristic of conn ected components in images is proposed. Theoretical definitions of morpholo gical leveling and morphological spectrum are used in the formal definition of a morphological characteristic, In multiscale segmentation, this charac teristic is formalized through the derivative of the morphological profile. Multiscale segmentation is particularly well suited for complex image scen es such as aerial or fine resolution satellite images, where very thin, env eloped and/or nested regions must be retained. The proposed method performs well in the presence of both low radiometric contrast and relatively low s patial resolution. Those factors may produce a textural effect, a border ef fect, and ambiguity in the object/background distinction. Segmentation exam ples for satellite images are given.