Scholarlink

The exponential increase of satellite launches in the past few decades has led to a significantly large population of debris objects in Earth’s orbit, particularly in the Low-Earth Orbit (LEO) regime. Their subsequent detection and monitoring have thus become ever more pertinent, with facilities such as the BIstatic RAdar for LEo Survey (BIRALES) space debris radar regularly used for detecting and tracking Resident Space Objects (RSOs) in LEO. The current detection pipeline installed at BIRALES employs the Multi-beam Streak Detection Strategy (MSDS) algorithm to identify and segment radar streaks in spectrogram data indicative of debris objects. In light of an upgrade planned for BIRALES, we aim to develop an ML streak detection model able to improve on the performance seen by the MSDS, in terms of recall and false positive rates at varying Signal-to-Noise (SNR) levels. These results serve as a springboard for future work in training a deployable model to rival and replace the MSDS detector.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine Learning Methods for Space Debris Detection in Bistatic Radar Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Miguel A. Zammit,
  • Andrea DeMarco,
  • Denis Cutajar,
  • Alessio Magro

摘要

The exponential increase of satellite launches in the past few decades has led to a significantly large population of debris objects in Earth’s orbit, particularly in the Low-Earth Orbit (LEO) regime. Their subsequent detection and monitoring have thus become ever more pertinent, with facilities such as the BIstatic RAdar for LEo Survey (BIRALES) space debris radar regularly used for detecting and tracking Resident Space Objects (RSOs) in LEO. The current detection pipeline installed at BIRALES employs the Multi-beam Streak Detection Strategy (MSDS) algorithm to identify and segment radar streaks in spectrogram data indicative of debris objects. In light of an upgrade planned for BIRALES, we aim to develop an ML streak detection model able to improve on the performance seen by the MSDS, in terms of recall and false positive rates at varying Signal-to-Noise (SNR) levels. These results serve as a springboard for future work in training a deployable model to rival and replace the MSDS detector.