Automatic Instantaneous Attitude Estimation Framework for Spacecraft Based on co-Located Optical/ISAR Observation

Instantaneous attitude estimation for spacecraft through optical/ISAR fusion observation is a hot topic in space situational awareness. However, due to the imaging characteristics and domain gap between the two data types, it is difficult to autonomously estimate instantaneous attitude based on data fusion. In this paper, an automatic optical/ISAR multi-feature fusion instantaneous attitude estimation framework is proposed. We deploy semantic feature extraction networks to extract and associate two kinds of robust features in optical and ISAR images, and an attitude estimation algorithm considering cross-range scaling based on multiple features combination is proposed. Meanwhile, the inherent structure constraints of spacecraft are introduced. Simulation experiments demonstrate that the proposed framework achieves an average attitude estimation accuracy of 1.87°, while also exhibiting excellent robustness.