Spectral Reconstruction from Thermal Infrared Multispectral Image Using Convolutional Neural Network and Transformer Joint Network
Remote Sensing · 05.04.2024 · 16 (7) · 1284
DOI: 10.3390/rs16071284 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 05.04.2024. Verfasst von Enyu Zhao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: General Program of National Nature Science Foundation of China.
Abstract (Originalsprache)
Thermal infrared remotely sensed data, by capturing the thermal radiation characteristics emitted by the Earth’s surface, plays a pivotal role in various domains, such as environmental monitoring, resource exploration, agricultural assessment, and disaster early warning. However, the acquisition of thermal infrared hyperspectral remotely sensed imagery necessitates more complex and higher-precision sensors, which in turn leads to higher research and operational costs. In this study, a novel Convolutional Neural Network (CNN)–Transformer combined block, termed CTBNet, is proposed to address the challenge of thermal infrared multispectral image spectral reconstruction. Specifically, the CTBNet comprises blocks that integrate CNN and Transformer technologies (CTB). Within these CTBs, an improved self-attention mechanism is introduced, which not only considers features across spatial and spectral dimensions concurrently, but also explicitly extracts incremental features from each channel. Compared to other algorithms, the proposed method more closely aligns with the true spectral curves in the reconstruction of hyperspectral images across the spectral dimension. Through a series of experiments, this approach has been proven to ensure robustness and generalizability, outperforming some state-of-the-art algorithms across various metrics.
Förderung
- General Program of National Nature Science Foundation of China
Zitieren
APA
Zhao, E., Qu, N., Wang, Y., & Gao, C. (2024). Spectral Reconstruction from Thermal Infrared Multispectral Image Using Convolutional Neural Network and Transformer Joint Network. Remote Sensing, 16(7), 1284. https://doi.org/10.3390/rs16071284
Vancouver
Zhao E, Qu N, Wang Y, Gao C. Spectral Reconstruction from Thermal Infrared Multispectral Image Using Convolutional Neural Network and Transformer Joint Network. Remote Sensing. 2024;16(7):1284. doi:10.3390/rs16071284
BibTeX
@article{Zhao2024,
author = {Zhao, Enyu and Qu, Nianxin and Wang, Yulei and Gao, Caixia},
title = {Spectral Reconstruction from Thermal Infrared Multispectral Image Using Convolutional Neural Network and Transformer Joint Network},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {7},
pages = {1284},
doi = {10.3390/rs16071284}
}
EUVIMED