OBJECT-BASED IMAGE ANALYSIS USING VERY HIGH-RESOLUTION SATELLITE DATA

Under the Additional Protocol of the Non-Proliferation Treaty (NPT), complementing the safeguards agreements between States and the International Atomic Energy Agency, commercial satellite imagery is an important source of information within the “information-driven safeguards” approach of the IAEA. The IAEA faces the challenge of a steadily increasing number of nuclear facilities worldwide and therefore (semi-) automated and computer driven methodologies can add a big value in the verification process. With regard to satellite imagery a large number of new commercial optical and SAR sensors with higher resolution, shorter revisiting time, more spectral bands, multiple polarizations, etc. has become available. Another challenge of the IAEA is to stay on top of these new technologies and to use them effectively and efficiently for nuclear verification. With the advances in satellite sensor technologies as to spatial resolution, the concept of object- based image analysis (OBIA) has been become widely-used in different remote sensing applications. By presenting some developments of OBIA algorithms and procedures, our paper aims at highlighting the advantages of applying OBIA approaches for nuclear verification. In detail, procedures for object-based change detection, object-based classification and GIS integration are to be demonstrated.