DEVELOPMENT OF A MULTI-DIMENSIONAL ARRAY DATABASE BASED MASSIVE SATELLITE INFORMATION PROCESSING AND ANALYSIS SYSTEM: KIWI-SAT

Abstract. Information and communication technology (ICT) is mainly applied to finance, telecommunications, and public sectors. However, since the early 2010s, there have been efforts to apply ICT to various fields such as aerospace, life science, energy, and automobiles. Recently, artificial intelligence and big data technologies have also been applied in the aerospace field, among others. In the field of aerospace, earth observation attracts the most interest.

One reason earth observation attracts such interest is that the availability of a satellite constellation allows more frequent observations of objects of interest. Another reason is the improvement of technologies that can process massive satellite images such as data cubes for urban change detection, disaster monitoring, and traffic analysis. When performing earth observation using satellite images, it is necessary to process a large amount of satellite information in real-time and analyze satellite images with artificial intelligence. Such research is continuing in various ways. The field of interest in this study is the processing technology for storing and retrieving large volumes of satellite images. Rasdaman and SciDB were two available open-source software applications.

In this paper, KIWI-Sat, which processes and analyzes a large amount of satellite imagery, mainly described and also show two KIWI-Sat demos with AI algorithms that are developed for Korean satellite images in KARI, one is super resolution algorithm of K3 and the other is water segmentation algorithm of K5, SAR satellite image.