Publication detail

Semantic Segmentation in Satellite Hyperspectral Imagery by Deep Learning

ALVAREZ JUSTO, J. GHIŢĂ, A. KOVÁČ, D. L. GARRETT, J. GEORGESCU, M. GONZALEZ-LLORENTE, J. TUDOR IONESCU, R. ARNE JOHANSEN, T.

Original Title

Semantic Segmentation in Satellite Hyperspectral Imagery by Deep Learning

Type

journal article in Web of Science

Language

English

Original Abstract

Satellites are increasingly adopting onboard AI to optimize operations and increase autonomy through in-orbit inference. The use of deep learning (DL) models for segmentation in hyperspectral imagery offers advantages for remote sensing applications. In this work, we train and test 20 models for multiclass segmentation in hyperspectral imagery, selected for their potential in future space deployment. These models include 1-D and 2-D convolutional neural networks (CNNs) and the latest vision transformers (ViTs). We propose a lightweight 1D-CNN model, 1D-Justo-LiuNet, which outperforms state-of-the-art models in the hypespectral domain. 1D-Justo-LiuNet exceeds the performance of 2D-CNN UNets and outperforms Apple's lightweight vision transformers designed for mobile inference. 1D-Justo-LiuNet achieves the highest accuracy (0.93) with the smallest model size (4563 parameters) among all tested models, while maintaining fast inference. Unlike 2D-CNNs and ViTs, which encode both spectral and spatial information, 1D-Justo-LiuNet focuses solely on the rich spectral features in hyperspectral data, benefitting from the high-dimensional feature space. Our findings are validated across various satellite datasets, with the HYPSO-1 mission serving as the primary case study for sea, land, and cloud segmentation. We further confirm our conclusions through generalization tests on other hyperspectral missions, such as NASA's EO-1. Based on its superior performance and compact size, we conclude that 1D-Justo-LiuNet is highly suitable for in-orbit deployment, providing an effective solution for optimizing and automating satellite operations at edge

Keywords

1D-CNNs; 2D-CNNs; deep learning (DL); remote sensing; satellite hyperspectral imagery; segmentation; vision transformers (ViTs)

Authors

ALVAREZ JUSTO, J.; GHIŢĂ, A.; KOVÁČ, D.; L. GARRETT, J.; GEORGESCU, M.; GONZALEZ-LLORENTE, J.; TUDOR IONESCU, R.; ARNE JOHANSEN, T.

Released

7. 11. 2024

Publisher

IEEE

Location

New York

ISBN

2151-1535

Periodical

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Year of study

18

Number

1

State

United States of America

Pages from

273

Pages to

293

Pages count

21

URL

https://ieeexplore.ieee.org/document/10746584

Full text in the Digital Library

http://hdl.handle.net/11012/250842

BibTex

@article{BUT193496,
  author="Jon {Alvarez Justo} and Alexandru {Ghiţă} and Daniel {Kováč} and Joseph {L. Garrett} and Mariana-Iuliana {Georgescu} and Jesus {Gonzalez-Llorente} and Radu {Tudor Ionescu} and Tor {Arne Johansen}",
  title="Semantic Segmentation in Satellite Hyperspectral Imagery by Deep Learning",
  journal="IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing",
  year="2024",
  volume="18",
  number="1",
  pages="273--293",
  doi="10.1109/JSTARS.2024.3487360",
  issn="2151-1535",
  url="https://ieeexplore.ieee.org/document/10746584"
}