Publication detail
Deep Learning for In-Orbit Cloud Segmentation and Classification in Hyperspectral Satellite Data
KOVÁČ, D. MUCHA, J. ALVAREZ JUSTO, J. MEKYSKA, J. GALÁŽ, Z. NOVOTNÝ, K. PITOŇÁK, R. KNĚŽÍK, J. HEREC, J. ARNE JOHANSEN, T.
Original Title
Deep Learning for In-Orbit Cloud Segmentation and Classification in Hyperspectral Satellite Data
Type
conference paper
Language
English
Original Abstract
This article explores the latest Convolutional Neural Networks (CNNs) for cloud detection aboard hyperspectral satel-lites. The performance of the 1D CNN (1D-Justo-LiuNet) and two 2D CNNs (nnU-net and 2D-Justo-UNet-Simple) for cloud segmentation and classification is assessed. Evaluation criteria include precision and computational efficiency for in-orbit deployment. Experiments utilize NASA's EO-1 Hyperion data, with different spectral channel numbers after Principal Component Analysis. Results indicate that 1D-Justo-LiuNet achieves the highest accu-racy, outperforming 2D CNNs, while maintaining compactness with larger spectral channel sets, albeit with increased inference times. However, the performance of 1D CNN degrades with significant channel reduction. In this context, the 2D-Justo-UNet-Simple offers a good balance for in-orbit deployment, considering precision, memory, and time costs. While nnU-net is suitable for on-ground processing, deployment of lightweight 1D-Justo-LiuNet is recommended for high-precision applications. Alternatively, lightweight 2D-Justo-UNet-Simple balanced better the computational cost and precision for in-orbit deployment.
Keywords
Hyperspectral Satellite Data; Cloud Segmentation; Classification; Convolutional Neural Networks; Principal Component Analysis
Authors
KOVÁČ, D.; MUCHA, J.; ALVAREZ JUSTO, J.; MEKYSKA, J.; GALÁŽ, Z.; NOVOTNÝ, K.; PITOŇÁK, R.; KNĚŽÍK, J.; HEREC, J.; ARNE JOHANSEN, T.
Released
13. 12. 2024
Publisher
IEEE
ISBN
979-8-3503-5323-5
Book
2024 9th International Conference on Frontiers of Signal Processing (ICFSP)
Pages from
68
Pages to
72
Pages count
5
URL
BibTex
@inproceedings{BUT193804,
author="Daniel {Kováč} and Ján {Mucha} and Jon {Alvarez Justo} and Jiří {Mekyska} and Zoltán {Galáž} and Kryštof {Novotný} and Radoslav {Pitoňák} and Jan {Kněžík} and Jonáš {Herec} and Tor {Arne Johansen}",
title="Deep Learning for In-Orbit Cloud Segmentation and Classification in Hyperspectral Satellite Data",
booktitle="2024 9th International Conference on Frontiers of Signal Processing (ICFSP)",
year="2024",
pages="68--72",
publisher="IEEE",
doi="10.1109/ICFSP62546.2024.10785468",
isbn="979-8-3503-5323-5",
url="https://doi.org/10.1109/ICFSP62546.2024.10785468"
}