Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

Jing Qin, Harlin Lee, Jocelyn T. Chi, Lucas Drumetz, Jocelyn Chanussot, Yifei Lou, Andrea L. Bertozzi

Research output: Contribution to journalArticlepeer-review

19 Scopus citations

Abstract

Remote sensing data from hyperspectral cameras suffer from limited spatial resolution, in which a single pixel of a hyperspectral image may contain information from several materials in the field of view. Blind hyperspectral image unmixing is the process of identifying the pure spectra of individual materials (i.e., endmembers) and their proportions (i.e., abundances) at each pixel. In this article, we propose a novel blind hyperspectral unmixing model based on the graph total variation (gTV) regularization, which can be solved efficiently by the alternating direction method of multipliers (ADMM). To further alleviate the computational cost, we apply the Nyström method to approximate a fully connected graph by a small subset of sampled points. Furthermore, we adopt the Merriman-Bence-Osher (MBO) scheme to solve the gTV-involved subproblem in ADMM by decomposing a gray-scale image into a bitwise form. A variety of numerical experiments on synthetic and real hyperspectral images are conducted, showcasing the potential of the proposed method in terms of identification accuracy and computational efficiency.

Original languageEnglish
Article number9200736
Pages (from-to)3338-3351
Number of pages14
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume59
Issue number4
DOIs
StatePublished - Apr 2021

Bibliographical note

Publisher Copyright:
© 1980-2012 IEEE.

Keywords

  • Alternating direction method of multipliers (ADMM)
  • Nyström method
  • blind hyperspectral unmixing
  • graph Laplacian
  • graph total variation (gTV)

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • General Earth and Planetary Sciences

Fingerprint

Dive into the research topics of 'Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization'. Together they form a unique fingerprint.

Cite this