Advanced search
1 file | 2.90 MB Add to list

Hyperspectral and multispectral image fusion via tensor sparsity regularization

Jize Xue (UGent) , Yongqiang Zhao, Wenzhi Liao (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
Hyperspectral image (HSI) super-resolution scheme based on HSI and multispectral image (MSI) fusion has been a prevalent research theme in remote sensing. However, most of the existing HSI-MSI fusion (HMF) methods adopt the sparsity prior across spatial or spectral domains via vectorizing hyperspectral cubes along a certain dimension, which results in the spatial or spectral informations distortion. Moreover, the current HMF works rarely pay attention to leveraging the nonlocal similar structure over spatial domain of the HSI. In this paper, we propose a new HSI-MSI fusion approach via tensor sparsity regularization which can encode essential spatial and spectral sparsity of an HSI. Specifically, we study how to utilize reasonably the sparsity of tensor to describe the spatialspectral correlation hidden in an HSI. Then, we resort to an efficient optimization strategy based on the alternative direction multiplier method (ADMM) for solving the resulting minimization problem. Experimental results on Pavia University data verify the merits of the proposed HMF algorithm.

Downloads

  • IGRASS Final.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 2.90 MB

Citation

Please use this url to cite or link to this publication:

MLA
Xue, Jize, et al. “Hyperspectral and Multispectral Image Fusion via Tensor Sparsity Regularization.” 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS19), IEEE, 2019.
APA
Xue, J., Zhao, Y., Liao, W., & Philips, W. (2019). Hyperspectral and multispectral image fusion via tensor sparsity regularization. In 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS19). Yokohama, Japan: IEEE.
Chicago author-date
Xue, Jize, Yongqiang Zhao, Wenzhi Liao, and Wilfried Philips. 2019. “Hyperspectral and Multispectral Image Fusion via Tensor Sparsity Regularization.” In 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS19). IEEE.
Chicago author-date (all authors)
Xue, Jize, Yongqiang Zhao, Wenzhi Liao, and Wilfried Philips. 2019. “Hyperspectral and Multispectral Image Fusion via Tensor Sparsity Regularization.” In 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS19). IEEE.
Vancouver
1.
Xue J, Zhao Y, Liao W, Philips W. Hyperspectral and multispectral image fusion via tensor sparsity regularization. In: 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS19). IEEE; 2019.
IEEE
[1]
J. Xue, Y. Zhao, W. Liao, and W. Philips, “Hyperspectral and multispectral image fusion via tensor sparsity regularization,” in 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS19), Yokohama, Japan, 2019.
@inproceedings{8668387,
  abstract     = {{Hyperspectral image (HSI) super-resolution scheme based on HSI and multispectral image (MSI) fusion has been a prevalent research theme in remote sensing. However, most of the existing HSI-MSI fusion (HMF) methods adopt the sparsity prior across spatial or spectral domains via vectorizing hyperspectral cubes along a certain dimension, which results in the spatial or spectral informations distortion. Moreover, the current HMF works rarely pay attention to leveraging the nonlocal similar structure over spatial domain of the HSI. In this paper, we propose a new HSI-MSI fusion approach via tensor sparsity regularization which can encode essential spatial and spectral sparsity of an HSI. Specifically, we study how to utilize reasonably the sparsity of tensor to describe the spatialspectral correlation hidden in an HSI. Then, we resort to an efficient optimization strategy based on the alternative direction multiplier method (ADMM) for solving the resulting minimization problem. Experimental results on Pavia University data verify the merits of the proposed HMF algorithm.}},
  author       = {{Xue, Jize and Zhao, Yongqiang and Liao, Wenzhi and Philips, Wilfried}},
  booktitle    = {{2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS19)}},
  language     = {{eng}},
  location     = {{Yokohama, Japan}},
  pages        = {{4}},
  publisher    = {{IEEE}},
  title        = {{Hyperspectral and multispectral image fusion via tensor sparsity regularization}},
  year         = {{2019}},
}