Deep learning-based space debris detection for space situational awareness: A feasibility study applied to the radar processing

Abstract

The increasing number of space objects (SO), debris, and constellation of satellites in Low Earth Orbit poses a significant threat to the sustainability and safety of space operations, which must be carefully and efficiently addressed to avoid mutual collisions. The space situational awareness is currently addressed by an ensemble of radar and radio-telescopes that detect and track SO. However, a large part of space debris is composed of very small and tiny metallic objects, very difficult to detect. The authors demonstrate the benefits of using deep learning (DL) architectures for small space object detection by radar observations. TIRA radio telescope has been simulated to generate range-Doppler maps, then used as inputs for object detection exploiting You-Only-Look-Once (YOLO) frameworks. The results demonstrate that the object detection by using YOLO algorithms outperform conventional target detection approaches, thus indicating the potential benefits of using DL techniques for space surveillance applications.