Satellite Pose Estimation Challenge: Dataset, Competition Design, and Results
Máté Kisantal, S. K. Sharma, Tae Ha Park, Dario Izzo, Marcus Märtens, Simone D’Amico
Abstract
Reliable pose estimation of uncooperative satellites is a key technology for enabling future on-orbit servicing and debris removal missions. The Kelvins Satellite Pose Estimation Challenge aims at evaluating and comparing monocular-vision-based approaches and pushing the state of the art on this problem. This article is based on the Satellite Pose Estimation Dataset, the first publicly available machine learning set of synthetic and real spacecraft imageries. The choice of dataset reflects one of the unique challenges associated with spaceborne computer vision tasks, namely the lack of spaceborne images to train and validate the developed algorithms. This article briefly reviews the basic properties and the collection process of the dataset that was made publicly available. The competition design, including the definition of performance metrics and the adopted testbed, is also discussed. The main contribution of this article is the analysis of the submissions of the 48 competitors, which compares the performance of different approaches and uncovers what factors make the satellite pose estimation problem especially challenging.