Spacecraft Pose Estimation Dataset (SPEED)

This repository contains Spacecraft PosE Estimation Dataset (SPEED), which is used to train and evaluate the performance of deep learning models for pose estimation of noncooperative spacecraft. SPEED consists of synthetic as well as actual camera images of a mock-up of the Tango spacecraft from the PRISMA mission. The synthetic images are created by fusing OpenGL-based renderings of the spacecraft’s 3D model with actual images of the Earth captured by the Himawari-8 meteorological satellite. The actual camera images are created using a 7 degrees-of-freedom robotic arm, which positions and orients a vision-based sensor with respect to a full-scale mock-up of the Tango spacecraft. Custom illumination devices simulate the Earth albedo and Sun light with high fidelity to emulate the illumination conditions present in space. SPEED was used in the international competition for spacecraft pose estimation co-hosted by the Advanced Concepts Team of the European Space Agency and the Space Rendezvous Laboratory of Stanford University.

本仓库所包含的航天器位姿估计数据集（Spacecraft PosE Estimation Dataset，SPEED），主要用于训练与评估面向非合作航天器位姿估计的深度学习模型的性能。该数据集涵盖两类图像：一是合成图像，二是PRISMA任务中Tango航天器样机的实拍相机图像。其中合成图像通过将基于OpenGL的航天器三维模型渲染结果，与由向日葵8号（Himawari-8）气象卫星捕获的地球实景图像融合生成；实拍相机图像则依托7自由度机械臂采集得到，该机械臂可对视觉传感器相对于全尺寸Tango航天器样机的位姿进行精准定位与定向。系统搭载定制化照明设备，以高保真度模拟地球反照与太阳光，复现太空环境中的真实照明条件。该数据集曾被用于由欧洲空间局先进概念团队与斯坦福大学空间交会实验室联合主办的国际航天器位姿估计竞赛。

搜集汇总

背景与挑战

背景概述

SPEED数据集是一个用于非合作航天器姿态估计的深度学习数据集，包含合成图像和实际相机图像，合成图像通过融合航天器3D模型渲染与真实地球图像生成，实际图像则利用高精度机械臂和光照模拟设备采集，以模拟太空环境。该数据集专为国际航天器姿态估计竞赛设计，发布于2022年，适用于卫星、计算机视觉和机器学习领域的研究。