논문 상세보기

Development of Semi-Automatic Satellite Imagery Analysis System to Support Monitoring of Potential Nuclear Activities

  • 언어ENG
  • URLhttps://db.koreascholar.com/Article/Detail/429785
모든 회원에게 무료로 제공됩니다.
한국방사성폐기물학회 학술논문요약집 (Abstracts of Proceedings of the Korean Radioactive Wasts Society)
한국방사성폐기물학회 (Korean Radioactive Waste Society)
초록

For countering nuclear proliferation, satellite imagery is being used to monitor suspicious nuclear activities in inaccessible countries or regions. Monitoring such activities involves detecting changes over time in nuclear facilities and their surroundings, and interpreting them based on prior knowledge in terms of nuclear proliferation or weaponisation. Therefore, analysts need to acquire and analyze satellite images periodically and have an understanding of nuclear fuel cycle as well as expertise in remote sensing. Meanwhile, as accessibility of satellite information has been increasing and accordingly a large amount of high-resolution satellite images is available, a lack of experts with expertise in both fields to perform satellite imagery analysis is being concerned. In this regard, the Institute of Korea Nonproliferation and Control (KINAC) has developed a prototype of semi-automatic satellite imagery analysis system that can support monitoring of potential nuclear activities to overcome the limitations of professionals and increase analysis efficiency. The system provides a satellite imagery database that can manage acquired images, and the users can load images from the database and analyze them in stages. The system includes a preprocessing module capable of resizing, correcting and matching images, a change detection module equipped with a pixel-object-based change detection algorithm for multi-temporal images, and a module that automatically generates reports with relevant information. In particular, this system continuously updates open-source information database related to potential nuclear activities and provides users with an integrated analytics platform that can support their interpretation by linking related images and textual information together. As such, the system could save time and cost in processing and interpreting satellite images by providing semi-automated analytic workflows for monitoring potential nuclear activities.

저자
  • Gayeon Ha(Korea Institute of Nuclear Nonproliferation and Control (KINAC)) Corresponding author
  • Jae-Jun Han(Korea Institute of Nuclear Nonproliferation and Control (KINAC))
  • Minsoo Kim(Korea Institute of Nuclear Nonproliferation and Control (KINAC))