发表机构
Universidad de Castilla–La Mancha; Universidad de Castilla-La Mancha; Escuela de Ingeniería Industrial y Aeroespacial de Toledo; Escuela Superior de Informática（卡斯蒂利亚-拉曼恰大学; 卡斯蒂利亚-拉曼恰大学; 托莱多工业与航空航天工程学院; 高等信息学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对纳卫星机载监视的下行链路瓶颈与数据集类别不平衡问题，提出结合星上推理与生成式数据增强的工作流，提升了检测精度与帧率，可作为实时自主监视的决策支持工具。
AI 中文摘要
低地球轨道的机载监视面临两个相互关联的瓶颈：纳卫星的下行链路预算有限，但传统方法仍需将数TB的原始图像传输至地面处理；公开的飞机卫星数据集稀缺且存在严重的类别不平衡问题。这些限制要么延误及时决策，要么导致标准检测器无法学习到稀有飞机类别的鲁棒表征。本文提出一种结合星上推理与生成式数据增强的工作流，以同时解决这两个问题。推理在配备低功耗边缘张量加速器的6U CubeSat上执行，而通过低秩适配微调的扩散模型生成合成的少数类图像。该合成输出由中间检测器自动标注为伪标签，并与经典增强样本合并。结果显示，平衡数据集使全局平均精度从77.9%提升至82.2%，少数类的F1值从0.683升至0.811；量化后的检测器适配片上内存，在轨投影帧率达25-30帧/秒。该方法与传统弯管架构（卫星作为被动数据收集器）形成对比，计算测试支持该工作流作为纳卫星实时自主机载监视的决策支持工具。
英文摘要
Airborne surveillance from low Earth orbit is hindered by two interconnected bottlenecks: nanosatellites have a limited downlink budget, yet the conventional approach still transmits terabytes of raw imagery to the ground for processing, and open satellite datasets for aircraft are scarce and severely class-imbalanced. These limitations either delay timely decision-making or prevent standard detectors from learning robust representations of rare aircraft classes. In this paper, a workflow that combines on-board inference with generative data augmentation is proposed to address both limitations jointly. Inference is executed on a 6U CubeSat equipped with a low-power edge tensor accelerator, while a diffusion model fine-tuned through low-rank adaptation generates synthetic minority-class imagery. This synthetic output is automatically annotated, pseudo-labelled, by an intermediate detector and merged with classically augmented samples. The results show that the balanced dataset increases global mean average precision from 77.9% to 82.2%, with the minority class rising from F1=0.683 to F1=0.811, and that the quantised detector fits the on-chip memory and projects 25-30 frames per second on orbit. This approach contrasts with the conventional bent-pipe architecture, in which the satellite acts as a passive data collector. Therefore, the computational tests support the proposed workflow as a decision-support tool for real-time, autonomous airborne surveillance from nanosatellites.
Comments43 pages, 14 figures
