Reconstructing Satellites in 3D from Amateur Telescope Images

2024-04-29

arXiv.org

AI Summary

3D reconstruction of low-Earth-orbit (LEO) satellites from amateur ground-based telescope videos faces severe challenges, including atmospheric turbulence, long-range observation, limited viewing angles, low signal-to-noise ratio, motion blur, and light pollution. Method: This paper proposes an enhanced 3D Gaussian Splatting framework incorporating joint pose-and-geometry optimization. It integrates satellite geometric priors for robust noise suppression and post-editing, deep learning–based image restoration, a customized Structure-from-Motion pipeline, and geometry-constrained point cloud refinement. Contribution/Results: Evaluated on real-world video sequences of the Tiangong Space Station and the International Space Station, the method substantially outperforms state-of-the-art approaches. It achieves, for the first time, high-fidelity, structurally coherent 3D point cloud reconstructions from sparse, highly noisy, short-exposure amateur observations. This establishes a novel, cost-effective paradigm for in-orbit monitoring of LEO satellites.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: 3D Computer Vision
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

This paper proposes a framework for the 3D reconstruction of satellites in low-Earth orbit, utilizing videos captured by small amateur telescopes. The video data obtained from these telescopes differ significantly from data for standard 3D reconstruction tasks, characterized by intense motion blur, atmospheric turbulence, pervasive background light pollution, extended focal length and constrained observational perspectives. To address these challenges, our approach begins with a comprehensive pre-processing workflow that encompasses deep learning-based image restoration, feature point extraction and camera pose initialization. We apply a customized Structure from Motion (SfM) approach, followed by an improved 3D Gaussian splatting algorithm, to achieve high-fidelity 3D model reconstruction. Our technique supports simultaneous 3D Gaussian training and pose estimation, enabling the robust generation of intricate 3D point clouds from sparse, noisy data. The procedure is further bolstered by a post-editing phase designed to eliminate noise points inconsistent with our prior knowledge of a satellite's geometric constraints. We validate our approach on synthetic datasets and actual observations of China's Space Station and International Space Station, showcasing its significant advantages over existing methods in reconstructing 3D space objects from ground-based observations.

Problem

• Reconstructing 3D satellite models from amateur telescope images
• Overcoming atmospheric turbulence and low signal-to-noise challenges
• Enabling cost-effective space situational awareness from Earth

Innovation

• Hybrid image pre-processing pipeline
• Joint pose estimation with Gaussian Splatting
• Branch-and-Bound search for 3D reconstruction