DISTRIBUTED UNMIXING OF HYPERSPECTRAL DATAWITH SPARSITY CONSTRAINT
Spectral unmixing (SU) is a data processing problem in hyperspectral remote sensing. The significant challenge in the SU problem is how to identify endmembers and their weights, accurately. For estimation of signature and fractional abundance matrices in a blind problem, nonnegative matrix factoriza...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2017-09-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4-W4/145/2017/isprs-archives-XLII-4-W4-145-2017.pdf |
| _version_ | 1811270162594136064 |
|---|---|
| author | S. Khoshsokhan R. Rajabi H. Zayyani |
| author_facet | S. Khoshsokhan R. Rajabi H. Zayyani |
| author_sort | S. Khoshsokhan |
| collection | DOAJ |
| description | Spectral unmixing (SU) is a data processing problem in hyperspectral remote sensing. The significant challenge in the SU problem is how to identify endmembers and their weights, accurately. For estimation of signature and fractional abundance matrices in a blind problem, nonnegative matrix factorization (NMF) and its developments are used widely in the SU problem. One of the constraints which was added to NMF is sparsity constraint that was regularized by L1/2 norm. In this paper, a new algorithm based on distributed optimization has been used for spectral unmixing. In the proposed algorithm, a network including single-node clusters has been employed. Each pixel in hyperspectral images considered as a node in this network. The distributed unmixing with sparsity constraint has been optimized with diffusion LMS strategy, and then the update equations for fractional abundance and signature matrices are obtained. Simulation results based on defined performance metrics, illustrate advantage of the proposed algorithm in spectral unmixing of hyperspectral data compared with other methods. The results show that the AAD and SAD of the proposed approach are improved respectively about 6 and 27 percent toward distributed unmixing in SNR=25dB. |
| first_indexed | 2024-04-12T21:55:57Z |
| format | Article |
| id | doaj.art-268ade8dd399491ab8cb9702c22cf452 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-04-12T21:55:57Z |
| publishDate | 2017-09-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-268ade8dd399491ab8cb9702c22cf4522022-12-22T03:15:20ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342017-09-01XLII-4-W414515010.5194/isprs-archives-XLII-4-W4-145-2017DISTRIBUTED UNMIXING OF HYPERSPECTRAL DATAWITH SPARSITY CONSTRAINTS. Khoshsokhan0R. Rajabi1H. Zayyani2Qom University of Technology, Electrical and Computer Engineering Department, Qom, IranQom University of Technology, Electrical and Computer Engineering Department, Qom, IranQom University of Technology, Electrical and Computer Engineering Department, Qom, IranSpectral unmixing (SU) is a data processing problem in hyperspectral remote sensing. The significant challenge in the SU problem is how to identify endmembers and their weights, accurately. For estimation of signature and fractional abundance matrices in a blind problem, nonnegative matrix factorization (NMF) and its developments are used widely in the SU problem. One of the constraints which was added to NMF is sparsity constraint that was regularized by L1/2 norm. In this paper, a new algorithm based on distributed optimization has been used for spectral unmixing. In the proposed algorithm, a network including single-node clusters has been employed. Each pixel in hyperspectral images considered as a node in this network. The distributed unmixing with sparsity constraint has been optimized with diffusion LMS strategy, and then the update equations for fractional abundance and signature matrices are obtained. Simulation results based on defined performance metrics, illustrate advantage of the proposed algorithm in spectral unmixing of hyperspectral data compared with other methods. The results show that the AAD and SAD of the proposed approach are improved respectively about 6 and 27 percent toward distributed unmixing in SNR=25dB.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4-W4/145/2017/isprs-archives-XLII-4-W4-145-2017.pdf |
| spellingShingle | S. Khoshsokhan R. Rajabi H. Zayyani DISTRIBUTED UNMIXING OF HYPERSPECTRAL DATAWITH SPARSITY CONSTRAINT The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | DISTRIBUTED UNMIXING OF HYPERSPECTRAL DATAWITH SPARSITY CONSTRAINT |
| title_full | DISTRIBUTED UNMIXING OF HYPERSPECTRAL DATAWITH SPARSITY CONSTRAINT |
| title_fullStr | DISTRIBUTED UNMIXING OF HYPERSPECTRAL DATAWITH SPARSITY CONSTRAINT |
| title_full_unstemmed | DISTRIBUTED UNMIXING OF HYPERSPECTRAL DATAWITH SPARSITY CONSTRAINT |
| title_short | DISTRIBUTED UNMIXING OF HYPERSPECTRAL DATAWITH SPARSITY CONSTRAINT |
| title_sort | distributed unmixing of hyperspectral datawith sparsity constraint |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4-W4/145/2017/isprs-archives-XLII-4-W4-145-2017.pdf |
| work_keys_str_mv | AT skhoshsokhan distributedunmixingofhyperspectraldatawithsparsityconstraint AT rrajabi distributedunmixingofhyperspectraldatawithsparsityconstraint AT hzayyani distributedunmixingofhyperspectraldatawithsparsityconstraint |