Change Detection in VHR Images Based on Sparse Representation of Morphological Attribute Profile

Change information of the earth’s surface is becoming more and more important in monitoring the local, regional and global resources and environment. For this reason , Change Detection has an increasing importance in the field of remote sensing. The image acquired by periodical passes of remote sensing satellites over the same areas permit a regular analysis of the changes that occurred on the ground. In this paper a new approach to change detection in very high resolution remote sensing images based on sparse representation of morphological attribute profile is presented. Attribute profiles allows the extraction of geometrical features related to the structure within the scene at different scales. The temporal changes are detected by comparing the geometrical features extracted from the image on each date. Morphological operators have been used in order to decrease the complexity of the image and extract spatial information. The operators are based on mathematical morphology, which is a theory for the analysis of spatial structures based on set theory.

Keywords— Change Detection, sparse representation, morphological attribute profile, remote sensing , very high rersolution imahges.