Satellite Detection in Unresolved Space Imagery for Space Domain Awareness Using Neural Networks

Abstract

This work utilizes a MobileNetV2 Convolutional Neural Network (CNN) for fast, mobile detection of satellites, and rejection of stars, in cluttered unresolved space imagery. First, a custom database is created using imagery from a synthetic satellite image program and labeled with bounding boxes over satellites for "satellitepositive" images. The CNN is then trained on this database and the inference is validated by checking the accuracy of the model on an external dataset constructed of real telescope imagery. In doing so, the trained CNN provides a method of rapid satellite identification for subsequent utilization in ground-based orbit estimation.

A space debris detection and tracking method for wide-field surveillance

“…Mastrofini et al 5 investigated an Artificial Intelligence(AI) approach for detect and track resident space objects. Jordan et al 6 utilized a MobileNetV2 Convolutional Neural Network (CNN) for the detection of space objects. 7 proposed a feature-based space objects detection method using CNN in ground-based electro-optical telescope imagery.…”