Spacecraft Pose Estimation

Competition organized by ESA and Space Rendezvous Lab (Stanford University).

Introduction

Accurate estimation of distance and orientation (pose) for objects in space are essential for many missions. When approaching an uncooperative target ,the pose can be estimated from camera images. In this challenge, you are tasked to estimate the pose of the Tango spacecraft from its synthetic and real images captured using computer graphics and a robotic testbed, respectively.

Dataset

The goal of this challenge is to estimate the pose, i.e., the relative position and attitude, of a known spacecraft from individual grayscale images. The 12000 synthetic images were generated to capture a variety of poses and illumination conditions and are sourced from two complimentary testbeds to validate the domain adaptation and transferability of the proposed approaches.

The dataset for this challenge was collected by the Space Rendezvous Laboratory (SLAB), and are part of SLAB’s Spacecraft PosE Estimation Dataset (SPEED) benchmark.

Example images with estimated axes.

Models

July 1st