EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Global Spatial-Spectral Feature Fused Autoencoder for Nonlinear Hyperspectral Unmixing

Mingle Zhang, Mingyu Yang, Hongyu Xie, Pinliang Yue, Wei Zhang, Qingbin Jiao, Liang Xu, Xin Tan

Remote Sensing · 26.08.2024 · 16 (17) · 3149

DOI: 10.3390/rs16173149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 26.08.2024. Verfasst von Mingle Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Changchun science and technology development plan project, Jilin province and Chinese Academy of Sciences Science and Technology Cooperation High Tech Special Fund project, Jilin Province Science and Technology Development Plan Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral unmixing (HU) aims to decompose mixed pixels into a set of endmembers and corresponding abundances. Deep learning-based HU methods are currently a hot research topic, but most existing unmixing methods still rely on per-pixel training or employ convolutional neural networks (CNNs), which overlook the non-local correlations of materials and spectral characteristics. Furthermore, current research mainly focuses on linear mixing models, which limits the feature extraction capability of deep encoders and further improvement in unmixing accuracy. In this paper, we propose a nonlinear unmixing network capable of extracting global spatial-spectral features. The network is designed based on an autoencoder architecture, where a dual-stream CNNs is employed in the encoder to separately extract spectral and local spatial information. The extracted features are then fused together to form a more complete representation of the input data. Subsequently, a linear projection-based multi-head self-attention mechanism is applied to capture global contextual information, allowing for comprehensive spatial information extraction while maintaining lightweight computation. To achieve better reconstruction performance, a model-free nonlinear mixing approach is adopted to enhance the model’s universality, with the mixing model learned entirely from the data. Additionally, an initialization method based on endmember bundles is utilized to reduce interference from outliers and noise. Comparative results on real datasets against several state-of-the-art unmixing methods demonstrate the superior of the proposed approach.

Förderung

  • Changchun science and technology development plan project
  • Jilin province and Chinese Academy of Sciences Science and Technology Cooperation High Tech Special Fund project
  • Jilin Province Science and Technology Development Plan Project
  • Scientific and Technological Innovation Project of Black Land Protection and Utilization
  • National Natural Science Foundation of China (NSFC)

Zitieren

APA

Zhang, M., Yang, M., Xie, H., Yue, P., Zhang, W., Jiao, Q., Xu, L., & Tan, X. (2024). A Global Spatial-Spectral Feature Fused Autoencoder for Nonlinear Hyperspectral Unmixing. Remote Sensing, 16(17), 3149. https://doi.org/10.3390/rs16173149

Vancouver

Zhang M, Yang M, Xie H, Yue P, Zhang W, Jiao Q, et al. A Global Spatial-Spectral Feature Fused Autoencoder for Nonlinear Hyperspectral Unmixing. Remote Sensing. 2024;16(17):3149. doi:10.3390/rs16173149

BibTeX
@article{Zhang2024,
  author = {Zhang, Mingle and Yang, Mingyu and Xie, Hongyu and Yue, Pinliang and Zhang, Wei and Jiao, Qingbin and Xu, Liang and Tan, Xin},
  title = {A Global Spatial-Spectral Feature Fused Autoencoder for Nonlinear Hyperspectral Unmixing},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {17},
  pages = {3149},
  doi = {10.3390/rs16173149}
}
Kostenlos starten →