Design and tests of filtering actions for an AI-based RSOs detection and tracking algorithm

Space debris represent a huge threat for the actual and future space traffic. The continuous monitoring of the space environment around the Earth and the build-up, maintenance of Resident Space Objects (RSOs) catalogue are essential to enhance the space segment safety. In the last few years, trend towards Space Based Space Surveillance (SBSS) missions was relevant. In particular, the monitoring of space debris through on-board Star Trackers (STs) coupled with Artificial Intelligence (AI) based algorithms is being studied, modeling RSOs as clear streaks on a dark background. This work presents the advances in the development of an AI-based algorithm for streaks-like RSOs Detection & Tracking for on-board optical sensors applications like STs. The initial design of the RSOs monitoring algorithm (Mastrofini et al., 2022) is extended and tested for what concerns the tracking part with new filtering actions. The goal is the improvement of the tracking outputs quality and reliability when multiple RSOs passages occur, with different configurations. Tests both on real and simulated images from STs are shown and discussed.