SatSplatYOLO：基于3D高斯泼溅的虚拟目标检测集成用于卫星特征识别
SatSplatYOLO: 3D Gaussian Splatting-based Virtual Object Detection Ensembles for Satellite Feature Recognition
AI总结：
针对在轨非合作卫星的自主交会需求，提出SatSplatYOLO方法，利用加速3D Gaussian splatting学习卫星3D表示并渲染虚拟视图，集成YOLOv5实现高置信度组件检测，支持星载自主制导与控制。
摘要：
在轨服务（OOS）、航天器检查和主动碎片清除（ADR）等任务，需要在非合作且可能未知的在轨空间目标附近进行精确的交会与近距操作。载人任务的安全问题和地面控制的延迟时间使得完全自主成为必然要求。本文提出一种方法，用于对在轨未知、非合作卫星的几何结构进行建图，并高置信度地检测其组件。我们实现了加速的3D Gaussian splatting以学习卫星的3D表示，渲染目标的虚拟视图，并在虚拟视图上集成YOLOv5目标检测器，从而实现可靠、准确且精确的卫星组件检测。该完整流水线能够在星载环境下运行，以支持自主制导、导航与控制任务所需的下游机器智能任务。
英文摘要：
On-orbit servicing (OOS), inspection of spacecraft, and active debris removal (ADR). Such missions require precise rendezvous and proximity operations in the vicinity of non-cooperative, possibly unknown, resident space objects. Safety concerns with manned missions and lag times with ground-based control necessitate complete autonomy. In this article, we present an approach for mapping geometries and high-confidence detection of components of unknown, non-cooperative satellites on orbit. We implement accelerated 3D Gaussian splatting to learn a 3D representation of the satellite, render virtual views of the target, and ensemble the YOLOv5 object detector over the virtual views, resulting in reliable, accurate, and precise satellite component detections. The full pipeline capable of running on-board and stand to enable downstream machine intelligence tasks necessary for autonomous guidance, navigation, and control tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
