Saved in:
Bibliographic Details
Main Authors: Wölki, Niklas, Kondmann, Lukas, Mollière, Christian, Langer, Martin, Gottfriedsen, Julia, Werner, Martin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.00357
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912681220374528
author Wölki, Niklas
Kondmann, Lukas
Mollière, Christian
Langer, Martin
Gottfriedsen, Julia
Werner, Martin
author_facet Wölki, Niklas
Kondmann, Lukas
Mollière, Christian
Langer, Martin
Gottfriedsen, Julia
Werner, Martin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00357
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transfer Learning for Onboard Cloud Segmentation in Thermal Earth Observation: From Landsat to a CubeSat Constellation
Wölki, Niklas
Kondmann, Lukas
Mollière, Christian
Langer, Martin
Gottfriedsen, Julia
Werner, Martin
Computer Vision and Pattern Recognition
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.
title Transfer Learning for Onboard Cloud Segmentation in Thermal Earth Observation: From Landsat to a CubeSat Constellation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.00357