Spectral and spatial character-based hyperspectral unmixing

Sen Jia, Yun Tao Qian, Zhen Ji, Lin Lin Shen

Research output: Journal PublicationArticlepeer-review

5 Citations (Scopus)


To represent the spectral and spatial character of hyperspectral data, by introducing the smoothness constraint of hyperspectral data and the sparseness constraint of spatial distribution of the materials, an improved nonnegative matrix factorization (INMF) was used for hyperspectral unmixing. Its monotonic convergence is guaranteed by using a gradient-based optimization algorithm. Experiments demonstrate that the INMF algorithm is yielding accurate estimation of both endmember spectra and abundance maps.

Original languageEnglish
Pages (from-to)262-267
Number of pages6
JournalShenzhen Daxue Xuebao (Ligong Ban)/Journal of Shenzhen University Science and Engineering
Issue number3
Publication statusPublished - Jul 2009
Externally publishedYes


  • Blind source separation
  • Hyperspectral unmixing
  • Linear spectral mixing model
  • Mixing pixel
  • Nonnegative matrix factorization

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Engineering (miscellaneous)


Dive into the research topics of 'Spectral and spatial character-based hyperspectral unmixing'. Together they form a unique fingerprint.

Cite this