Image Classification for Automated Image Cross-Correlation Applications in the Geosciences

In Earth Science, image cross-correlation (ICC) can be used to identify the evolution of active processes. However, this technology can be ineective, because it is sometimes dicult to visualize certain phenomena, and surface roughness can cause shadows. In such instances, manual image selection is required to select images that are suitably illuminated, and in which visibility is adequate. This impedes the development of an autonomous system applied to ICC in monitoring applications. In this paper, the uncertainty introduced by the presence of shadows is quantitatively analysed, and a method suitable for ICC applications is proposed: The method automatically selects images, and is based on a supervised classification of images using the support vector machine. According to visual and illumination conditions, the images are divided into three classes: (i) No visibility, (ii) direct illumination and (iii) diuse illumination. Images belonging to the diuse illumination class are used in cross-correlation processing. Finally, an operative procedure is presented for applying the automated ICC processing chain in geoscience monitoring applications.