Journal
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
Volume 11, Issue 4, Pages 1022-1029Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2018.2805779
Keywords
Hyperspectral unmixing; group low-rank non-negative; matrix factorization (GLrNMF); low-rank; semantic regularizer; spatial-spectral
Categories
Funding
- National Natural Science Foundation of China [61771380, U1730109, 91438103, 61771376, 91438201, U1701267, 61703328]
- Equipment preresearch project of the 13th FiveYears Plan [6140137050206, 414120101026, 6140312010103, 6141A020223, 6141B06160301, 6141B07090102]
- Major Research Plan in Shaanxi Province of China [2017ZDXM-GY-103, 017ZDCXL-GY-03-02]
- Foundation of the State Key Laboratory of CEMEE [2017K0202B, 2018K0101B]
- Science Basis Research Program in Shaanxi Province of China [16JK1823, 2017JM6086]
Ask authors/readers for more resources
In this paper, the low rank prior of abundances of hyperspectral data is explored and combined with semantic information to develop a newGroup Low-rank constrainedNonnegative Matrix Factorization (GLrNMF) method for linear hyperspectral unmixing. First, hyperspectral image pixels are divided into several groups of superpixels, and then low-rank constraints are cast on them to explore the semantic geometry in both spatial and spectral domains. By incorporating semantic information into the NMF, we can recover more accurate endmembers and abundances in the linear unmixing model. Some experiments are taken on several synthetic and real hyperspectral data to investigate the performance of GLrNMF, and the results show that it can outperform some state-of-the-art unmixing results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available