Integrated Spatio-Spectral-Temporal Fusion via Anisotropic Sparsity Constrained Low-Rank Tensor Approximation

Wei Li, Yinjian Wang*, Na Liu, Chenchao Xiao, Zhiwei Sun, Qian Du

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)
Plum Print visual indicator of research metrics
  • Citations
    • Citation Indexes: 4
  • Captures
    • Readers: 1
see details

Abstract

Although spatio-spectral and spatio-temporal fusion has been well explored, few efforts are made on integrating spatio-spectral-temporal features. As an intrinsic prior, low tensor rank has been successfully taken into effect by current fusion models, most of which, however, resort to establishing an overall low-rank norm without performing factorization techniques and thus have trouble capturing the latent high-order structure of hyperspectral data cube. To address that, a novel anisotropic sparsity (AS) tensor norm is developed to make the rank minimization a learnable process under the Tucker decomposition. The AS norm enables the model to minimize the multilinear tensor ranks if imposed on the core tensor after factorization; hence, it significantly improves the model's fusion performance. In the temporal domain, a Hadamard-product-based variability descriptor is incorporated into the fusion model to map the former information to the current time. In addition, piecewise smooth prior of the Tucker factors is employed by extra regularizers as supplement to the loss of spatial information. With the proximal differential matrix being developed for optimization, the proposed method reaches state-of-the-art results on both spatio-spectral and spatio-spectral-temporal fusion at a low computational cost.

Original languageEnglish
Article number5517416
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume61
DOIs
Publication statusPublished - 2023

Keywords

  • Hyperspectral image (HSI) and multispectral image (MSI)
  • low-rank tensor
  • remote sensing
  • spatio-spectral-temporal fusion

Fingerprint

Dive into the research topics of 'Integrated Spatio-Spectral-Temporal Fusion via Anisotropic Sparsity Constrained Low-Rank Tensor Approximation'. Together they form a unique fingerprint.

Cite this

Li, W., Wang, Y., Liu, N., Xiao, C., Sun, Z., & Du, Q. (2023). Integrated Spatio-Spectral-Temporal Fusion via Anisotropic Sparsity Constrained Low-Rank Tensor Approximation. IEEE Transactions on Geoscience and Remote Sensing, 61, Article 5517416. https://doi.org/10.1109/TGRS.2023.3284481