Space object classification and characterization via Multiple Model Adaptive Estimation

In recent years there has been an increase in the number of inactive and debris objects in space. The characterization of the uncertainty in the knowledge of these Space Objects (SOs) is very important in developing an understanding of the space debris fields and any present or future threat they may pose. This work examines classification based on Multiple Model Adaptive Estimation (MMAE) to extract SO characteristics from observations while estimating the probability the observations belong to a given class of objects. Recovering these characteristics and trajectories with sufficient accuracy is shown in this paper, where the characteristics are inherent in unique SO models used in the MMAE filter bank. A number of scenarios are shown to highlight the effectiveness of the proposed classification approach. The performance of this strategy is demonstrated via simulated scenarios.