用公开数据训练轻量模型，实现星载热红外云检测
Transfer Learning for Onboard Cloud Segmentation in Thermal Earth Observation: From Landsat to a CubeSat Constellation
- 用Landsat数据预训练，再用少量任务数据微调
- 宏F1提升至0.877，5秒内完成全图推理
- 适合算力有限的立方星热红外任务
星载云分割在热红外地球观测中至关重要却研究不足，尤其对硬件受限、仅具单一热波段的立方星任务而言。传统云掩膜方法因缺乏标注数据难以适用。本文针对FOREST-2立方星，采用轻量级MobileNet编码器的UNet结构，先在公开的Landsat-7云覆盖评估数据集上预训练，再以少量任务特定样本进行联合微调，使宏平均F1从仅基于FOREST-2数据的基线0.850提升至0.877。模型转换为TensorRT引擎后，在NVIDIA Jetson Nano上实现全图推理时间低于5秒。结果表明，结合公开数据与轻量架构，可在轨实现高精度、低延迟的纯热红外云掩膜，支持数据受限任务中的实时决策。
原文摘要 · Abstract (English)
Onboard cloud segmentation is a critical yet underexplored task in thermal Earth observation (EO), particularly for CubeSat missions constrained by limited hardware and spectral information. CubeSats often rely on a single thermal band and lack sufficient labeled data, making conventional cloud masking techniques infeasible. This work addresses these challenges by applying transfer learning to thermal cloud segmentation for the FOREST-2 CubeSat, using a UNet with a lightweight MobileNet encoder. We pretrain the model on the public Landsat-7 Cloud Cover Assessment Dataset and fine-tune it with a small set of mission-specific samples in a joint-training setup, improving the macro F1 from 0.850 to 0.877 over FOREST-2-only baselines. We convert the model to a TensorRT engine and demonstrate full-image inference in under 5 seconds on an NVIDIA Jetson Nano. These results show that leveraging public datasets and lightweight architectures can enable accurate, efficient thermal-only cloud masking on-orbit, supporting real-time decision-making in data-limited EO missions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。