Using Low-Rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing

Lianru Gao, Zhicheng Wang, Lina ZHUANG, Haoyang Yu, Bing Zhang, Jocelyn Chanussot

Research output: Contribution to journalArticlepeer-review

Abstract

Tensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a hyperspectral image (HSI) cube can be naturally represented as a third-order tensor, which can perfectly retain the spatial information in the image. In this article, we extend the linear tensor method to the nonlinear tensor method and propose a nonlinear low-rank tensor unmixing algorithm to solve the generalized bilinear model (GBM). Specifically, the linear and nonlinear parts of the GBM can both be expressed as tensors. Furthermore, the low-rank structures of abundance maps and nonlinear interaction abundance maps are exploited by minimizing their nuclear norm, thus taking full advantage of the high spatial correlation in HSIs. Synthetic and real-data experiments show that the low rank of abundance maps and nonlinear interaction abundance maps exploited in our method can improve the performance of the nonlinear unmixing. A MATLAB demo of this work will be available at https://github.com/LinaZhuang for the sake of reproducibility.

Original languageEnglish
Number of pages17
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume60
Early online date25 Mar 2021
DOIs
Publication statusPublished - Jan 2022

Scopus Subject Areas

  • Electrical and Electronic Engineering
  • Earth and Planetary Sciences(all)

User-Defined Keywords

  • Hyperspectral image (HSI)
  • Tensor decomposition
  • Low rank
  • Nonlinear unmixing

Fingerprint

Dive into the research topics of 'Using Low-Rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing'. Together they form a unique fingerprint.

Cite this