发表机构
Maastricht University; University of Arizona; Polytechnic University of Bari（马斯特里赫特大学; 亚利桑那大学; 巴里理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出结合Tiny-U-Net与astro-VAE的深度学习流水线，通过恒星去除和背景重建预处理，提升地月空间光学图像中微弱运动目标的检测能力。
AI 中文摘要
我们提出了一种深度学习流水线，通过自动化恒星去除和背景重建来增强光学空间态势感知（SSA）图像中微弱运动目标的检测。在光学观测中，检测低信噪比（SNR）目标仍然极具挑战性，尤其是在地月空间（X-GEO）环境中，结构化的天空背景、密集的恒星场和散射的月光显著降低了经典检测算法的性能。为解决这一问题，所提出的流水线将轻量级分割网络（Tiny-U-Net）用于生成恒星掩膜，并与部分卷积变分自编码器（astro-VAE）相结合，后者旨在学习天文背景的统计分布，并对掩膜区域进行上下文感知的修复。重建后的背景图随后可作为预处理步骤，在检测前抑制固定源和背景不均匀性。作为概念验证，该方法与移位叠加方案集成，并在针对X-GEO区域的地基望远镜真实观测数据上进行了评估。结果表明，该方法能够高保真地重建无恒星背景，同时保留运动目标并显著增强其可检测性，从而为光学SSA场景中的微弱运动目标检测提供了一种有效的数据驱动预处理策略。
英文摘要
We present a deep-learning pipeline for enhancing the detection of faint moving objects in optical space situational awareness (SSA) imagery through automated star removal and background reconstruction. Detecting low signal-to-noise ratio (SNR) objects remains extremely challenging in optical observations, particularly in the cislunar (X-GEO) environment, where structured sky backgrounds, dense stellar fields, and scattered moonlight significantly degrade the performance of classical detection algorithms. To address this problem, the proposed pipeline combines a lightweight segmentation network (Tiny-U-Net) to generate stellar masks with a partial-convolution variational autoencoder (astro-VAE), designed to learn the statistical distribution of astronomical backgrounds and perform context-aware inpainting of masked regions. The reconstructed background maps can then be used as a preprocessing step to suppress fixed sources and background inhomogeneities prior to detection. As a proof of concept, the approach is integrated with a shift-and-stack scheme and evaluated on real ground-based telescope observations targeting the X-GEO region. Results demonstrate that the method reconstructs star-free backgrounds with high fidelity, while preserving moving targets and significantly enhancing detectability, thereby providing an effective data-driven preprocessing strategy for faint moving-object detection in optical SSA scenarios.
CommentsAccepted at SPAICE 2026: the 3rd European Space Agency Conference on AI in and for Space
