A multilevel approach to change detection for port surveillance with very high resolution SAR images

This paper proposes an approach to change detection in very high geometrical resolution (VHR) multitemporal SAR images for hot spot surveillance. The proposed approach is based on two concepts: i) the use of backscattering information extracted at different resolution levels; and ii) the use of prior information usually available on hot spots. Here the proposed approach is designed for the solution of a surveillance problem in port areas. To this end a data set was used made up of a pair of multitemporal VHR SAR images acquired by the COSMO-SkyMed (CSK®) constellation in spotlight mode over the commercial port of Livorno (Italy). These images define a complex change-detection problem due to the different kinds of changes on the ground, the high spatial resolution and the complexity of object backscattering in the considered area. Experimental results point out the effectiveness of the proposed approach.