Nanosatellites leverage AI for autonomous aircraft surveillance

Researchers have developed a novel workflow for autonomous aircraft surveillance from nanosatellites, addressing limitations in downlink budget and scarce training data. The system utilizes on-board inference on a CubeSat with a low-power edge tensor accelerator, combined with a diffusion model fine-tuned via Low Rank Adaptation to generate synthetic imagery for rare aircraft classes. This approach significantly improves detection accuracy, increasing global mean average precision and enhancing the F1 score for minority classes, while also enabling real-time processing capabilities. AI

IMPACT Enables real-time, autonomous airborne surveillance from nanosatellites by overcoming data limitations.

RANK_REASON The cluster contains a research paper detailing a novel technical approach. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• CatalyzeX
• CubeSat
• DagsHub
• David Muñoz-Valero
• diffusion model
• Hugging Face
• Low Rank Adaptation
• Nanosatellites for quantum science and technology

• paper
• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →