EUVIMEDEUVIMED entdecken
Crossref

Coupled Matrix Factorization Constrained Deep Hyperspectral and Multispectral Image Fusion

Xiaoyang Wu, Song Xiao, Wenqian Dong, Jiahui Qu, Tongzhen Zhang, Yunsong Li

IEEE Sensors Journal · 01.03.2024 · 24 (5) · 6392-6404

DOI: 10.1109/jsen.2023.3347564 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.03.2024. Verfasst von Xiaoyang Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: Young Talent Fund of Xi’an Association for Science and Technology, National Natural Science Foundation of China, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The application of convolutional neural networks (CNNs) has yielded remarkable outcomes in the fusion of hyperspectral and multispectral images (HSI+MSI). However, most existing researches design black-box models for the direct reconstruction of high-resolution images from low-resolution images, which cannot theoretically guarantee the fusion mechanism throughout the network flow, thus limiting the restoration accuracy. This article proposes a novel coupled matrix factorization (CMF) constrained deep interpretable network for HSI+MSI fusion, termed as CMF-FUSnet. Specifically, the iterative process of CMF is unfolded into a two-branch network interwoven with multiple denoiser modules and matrix factorization modules. In each iteration, the CMF-encoded two-branch sub-network alternately decomposes HSI and MSI to estimate their abundance and endmember matrices, respectively. High-resolution HSI can be obtained by multiplying the endmembers extracted from the HSI and the abundances extracted from the MSI. The benefit is that the proposed CMF-FUSnet breaks through the black-box operation mode while adopting an end-to-end data-driven model, realizes the embedding of physical meaning, and improves the generalization of the model. Numerical experiments show that our proposed CMF-FUSnet compares favorably with both state-of-the-art model-driven and data-driven fusion methods in terms of visual analysis and quality assessment.

Förderung

  • Young Talent Fund of Xi’an Association for Science and Technology
  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • China Postdoctoral Science Special Foundation
  • Young Talent Fund of Association for Science and Technology in Shaanxi
  • Youth Innovation Team of Shaanxi Universities

Zitieren

APA

Wu, X., Xiao, S., Dong, W., Qu, J., Zhang, T., & Li, Y. (2024). Coupled Matrix Factorization Constrained Deep Hyperspectral and Multispectral Image Fusion. IEEE Sensors Journal, 24(5), 6392-6404. https://doi.org/10.1109/jsen.2023.3347564

Vancouver

Wu X, Xiao S, Dong W, Qu J, Zhang T, Li Y. Coupled Matrix Factorization Constrained Deep Hyperspectral and Multispectral Image Fusion. IEEE Sensors Journal. 2024;24(5):6392-6404. doi:10.1109/jsen.2023.3347564

BibTeX
@article{Wu2024,
  author = {Wu, Xiaoyang and Xiao, Song and Dong, Wenqian and Qu, Jiahui and Zhang, Tongzhen and Li, Yunsong},
  title = {Coupled Matrix Factorization Constrained Deep Hyperspectral and Multispectral Image Fusion},
  journal = {IEEE Sensors Journal},
  year = {2024},
  volume = {24},
  number = {5},
  pages = {6392--6404},
  doi = {10.1109/jsen.2023.3347564}
}
Kostenlos starten →