FUSING MULTI-MODAL DATA FOR SUPERVISED CHANGE DETECTION

Abstract. With the rapid development of remote sensing technology in last decade, different modalities data recorded via a variety sensors are now easily accessible. Different often provide complementary information and thus more detailed accurate Earth observation is possible by integrating their joint information. While change detection methods have been traditionally proposed for homogeneous data, combining multi-sensor multi-temporal with characteristics resolution may robust interpretation spatio-temporal evolution. However, integration from disparate sensory sources challenging. Moreover, research this direction hindered lack available multi-modal sets. To resolve these current shortcomings we curate novel set detection. We further propose Siamese architecture fusion SAR optical observations detection, which underlines value our newly gathered data. An experimental validation on aforementioned demonstrates potentials model, outperforms common mono-modal compared against.