Resident Space Object Feature Identification and Attitude Detection using Hierarchical Mixtures of Experts
Abstract
Space Domain Awareness (SDA) involves detecting, tracking, identifying and characterizing resident space objects (RSOs). This paper proposes an algorithm based on a Hierarchical Mixture of Experts (HME) for identifying RSO features and determining an RSO's attitude profile from astrometric and non-resolved photometric observations. This paper discusses the mathematical background of the HME; the assumptions, test scenarios, and results of processing simulated apparent magnitude and angles data. The results show that the HME is capable of detecting the size, shape, reflectivity, and maneuvers performed by an RSO. The HME is also shown to be capable of identifying and distinguishing between nadir pointing, sun-pointing, and spinning objects even though none of the experts in the HME is directly estimating attitude.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2013
- Accession Number
- AD1148895
Entities
People
- Angelica Ceniceros
- David E. Gaylor
- Elfego Iii Pinon
- Jessica T. Anderson
Organizations
- Emergent Space Technologies (United States)
- University of Arizona