The purpose of space surveillance is to classify and, if possible, assess the mission and performance capabilities of space objects. Historically, imaging techniques have obtained useful results. However, with the advances achieved in microtechnologies, small but highly functional satellites (largest dimension <1 m) are emerging that are hard to identify by imaging with large ground-based telescopes. The concept of using nonimaging measurements to obtain information is relatively new. In this paper, we present and discuss the performance of two techniques for classifying satellites based on spectral measurements. A distance-based classifier and a neural-net-based classifier are used to process both calibrated spectral data and features computed using these data. Neural networks are found to give better recognition results than the distance-based classifier, and once trained, this method is also faster. The average error rates for the distance-based method are greater than 30% when the inputs are the calibrated spectra, and 70% when using the central moments and the K-nearest-neighbors method. The best results are obtained for the neural network design, with the lowest class error rate at 0% for some satellites, the highest error rate at 30%, and an average error rate at 16%.
The proliferation of small, lightweight, 'micro-' and 'nanosatellite' (largest dimension < 1m ) has presented new challenges to the space surveillance community. The small size of these satellites makes them unresolvable by ground-based imaging systems. The core concept of using Non-Imaging Measurements (NIM) to gather information about these objects comes from the fact that after reflection on a satellite surface, the reflected light contains information about the surface materials of the satellite. This approach of using NIM for satellite evaluation is relatively new. In this paper, we discuss the accuracy of using these spectral measurements to match an unknown spectrum to a database containing known spectra. Several approaches have been developed and are presented in this paper. The first method is an artificial neural network designed to process central moments of real measured spectra. This spectrum database is the Spica database
provided by the Maui Surveillance Site (MSSS), Hawaii USA and
consists in spectra from more than 100 different satellites. The
average rate of correct identification is 84%. The second approach is based on the ability of spectral signal processing to estimate relative abundances of materials from the measurement of a single spectrum; this method is called spectral unmixing. Material spectra were provided by the NASA Johnson Space Center (JSC) to create synthetic spectra. An approach based on the Expectation Maximization (EM) algorithm was used to estimate relative abundances and presence of materials in a synthetic spectrum. The results for material identification and abundance estimation are presented as a function of signal-to-noise ratio. For the EM method, the overall correct estimation rate is 95.1% and the average error on the fractional composition estimation is 19.7%.