SPARK: SPAcecraft Recognition leveraging Knowledge of Space Environment

TL;DR

The paper introduces the SPARK dataset, a large multi-modal space object dataset designed to advance spacecraft recognition research under realistic space conditions.

Contribution

It presents a new, diverse, multi-modal dataset for space object recognition, enabling benchmarking and development of data-driven algorithms in space environments.

Findings

Dataset contains 150k images per modality, RGB and depth.

Preliminary experiments validate dataset relevance and highlight space-specific challenges.

Dataset supports development of recognition, classification, and detection algorithms.

Abstract

This paper proposes the SPARK dataset as a new unique space object multi-modal image dataset. Image-based object recognition is an important component of Space Situational Awareness, especially for applications such as on-orbit servicing, active debris removal, and satellite formation. However, the lack of sufficient annotated space data has limited research efforts in developing data-driven spacecraft recognition approaches. The SPARK dataset has been generated under a realistic space simulation environment, with a large diversity in sensing conditions for different orbital scenarios. It provides about 150k images per modality, RGB and depth, and 11 classes for spacecrafts and debris. This dataset offers an opportunity to benchmark and further develop object recognition, classification and detection algorithms, as well as multi-modal RGB-Depth approaches under space sensing conditions. Preliminary experimental evaluation validates the relevance of the data, and highlights interesting challenging scenarios specific to the space environment.