Collaborative Space Object Detection with Multi-Satellite Viewpoints in LEO Constellations

2026-06-01

AI Summary

The rapid proliferation of satellites in low Earth orbit has intensified space congestion, creating an urgent need for efficient on-orbit space object detection under stringent onboard resource constraints. This work presents the first systematic exploration of multi-view fusion detection leveraging coordinated observations from multiple low-Earth-orbit satellites. We propose a satellite-deployable multi-view input representation and fusion strategy, enabling joint processing of RGB and grayscale imagery based on models such as YOLOv9. Experimental results demonstrate that fusing three views significantly enhances detection performance: for YOLOv9-m, mAP50 improves from 0.638 to 0.732 and mAP50–95 from 0.227 to 0.276. Under the optimal grayscale configuration, these metrics increase by 36.3% and 46.5%, respectively.

Abstract

With the growing number of satellites in low Earth orbit (LEO) constellations, the near-Earth space environment has become increasingly congested, making space object detection (SOD) a pressing challenge for space safety and sustainability. To mitigate collision risks and ensure the continuity of space operations, SOD systems must deliver fast and accurate detection under stringent onboard constraints. In this paper, we investigate the potential of multi-viewpoint observation fusion within a deep learning (DL) framework to enhance SOD performance. We design a practical multi-view pipeline and several input representations for feeding multi-view data into YOLO-based detectors. Our experiments show that using multi-view inputs is feasible in most cases and typically produces better results for mAP50 and mAP50-95. For example, in model YOLOv9-m, single-view compared to a three-view fused RGB setting, mAP50 increases from 0.638 to 0.732, while mAP50-95 improves from 0.227 to 0.276. Compared with the single-view setting, the best three-view grayscale configuration improves mAP50 by 36.3% and mAP50-95 by 46.5%. These findings establish multi-view fusion as a viable and effective strategy for SOD, with broad implications for space situational awareness in LEO constellation deployments.

Problem

• space object detection
• LEO constellations
• multi-satellite viewpoints
• space situational awareness
• collision risk

Innovation

• multi-view fusion
• space object detection
• LEO constellations
• deep learning
• YOLO-based detectors