Abstract

Sparse unmixing has been proven to be an effective method for hyperspectral unmixing. Hyperspectral images contain rich spectral and spatial information. The means to make full use of spectral information, spatial information, and enhanced sparsity constraints are the main research directions to improve the accuracy of sparse unmixing. However, many algorithms only focus on one or two of these factors, because it is difficult to construct an unmixing model that considers all three factors. To address this issue, a novel algorithm called multiview-based spectral weighted and low-rank row-sparsity unmixing is proposed. A multiview data set is generated through spectral partitioning, and then spectral weighting is imposed on it to exploit the abundant spectral information. The row-sparsity approach, which controls the sparsity by the l2,0 norm, outperforms the single-sparsity approach in many scenarios. Many algorithms use convex relaxation methods to solve the l2,0 norm to avoid the NP-hard problem, but this will reduce sparsity and unmixing accuracy. In this paper, a row-hard-threshold function is introduced to solve the l2,0 norm directly, which guarantees the sparsity of the results. The high spatial correlation of hyperspectral images is associated with low column rank; therefore, the low-rank constraint is adopted to utilize spatial information. Experiments with simulated and real data prove that the proposed algorithm can obtain better unmixing results.

PDF Article

References

  • View by:

  1. N. Keshava and J. F. Mustard2002Spectral unmixingIEEE Signal Process. Mag.194457
  2. J. M. Bioucas-Dias, A. Plaza, N. Dobigeon, M. Parente, Q. Du, P. Gader, and J. Chanussot2012Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approachesIEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.5354379
  3. M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza2011Sparse unmixing of hyperspectral dataIEEE Trans. Geosci. Remote Sens.4920142039
  4. M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza2014Collaborative sparse regression for hyperspectral unmixingIEEE Trans. Geosci. Remote Sens.52341354
  5. C. Y. Zheng, H. Li, Q. Wang, and C. L. P. Chen2016Reweighted sparse regression for hyperspectral unmixingIEEE Trans. Geosci. Remote Sens.54479488
  6. R. Wang, H.-C. Li, W. Liao, and A. Pi┼żuricaDouble reweighted sparse regression for hyperspectral unmixingProc. IEEE International Geoscience and Remote Sensing Symposium - IGARSSJul. 2016Beijing, China69866989
  7. Z. Shi, T. Shi, M. Zhou, and X. Xu2018Collaborative sparse hyperspectral unmixing using l0 normIEEE Trans. Geosci. Remote Sens.5654955508
  8. M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza2012Total variation spatial regularization for sparse hyperspectral unmixingIEEE Trans. Geosci. Remote Sens.5044844502
  9. X. Li, J. Huang, L.-J. Deng, and T.-Z. Huang2019Bilateral filter based total variation regularization for sparse hyperspectral image unmixingInf. Sci.504334353
  10. J. Huang, T.-Z. Huang, X.-L. Zhao, and L.-J. Deng2019Joint-sparse-blocks regression for total variation regularized hyperspectral unmixingIEEE Access7138779138791
  11. S. Zhang, J. Li, H.-C. Li, C. Deng, and A. Plaza2018Spectral-spatial weighted sparse regression for hyperspectral image unmixingIEEE Trans. Geosci. Remote Sens.5632653276
  12. P. V. Giampouras, K. E. Themelis, A. A. Rontogiannis, and K. D. Koutroumbas2016Simultaneously sparse and low-rank abundance matrix estimation for hyperspectral image unmixingIEEE Trans. Geosci. Remote Sens.5447754789
  13. J. Huang, T. Z. Huang, L. J. Deng, and X. L. Zhao2019Joint-sparse-blocks and low-rank representation for hyperspectral unmixingIEEE Trans. Geosci. Remote Sens.5724192438
  14. H. Han, G. Wang, M. Wang, J. Miao, S. Guo, L. Chen, M. Zhang, and K. Guo2020Hyperspectral unmixing via nonconvex sparse and low-rank constraintIEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.1357045718
  15. R. Ammanouil, J. A. Melhem, J. Farah, and P. HoneineSpectral partitioning and fusion techniques for hyperspectral data classification and unmixingProc. 6th International Symposium on Communications, Control and Signal Processing - ISCCSPMay. 2014Athens, Greece550553
  16. L. Qi, J. Li, Y. Wang, and X. Gao2019Region-based multiview sparse hyperspectral unmixing incorporating spectral libraryIEEE Geosci. Remote Sens. Lett.1611401144
  17. L. Qi, J. Li, Y. Wang, Y. Huang, and X. Gao2020Spectral-spatial-weighted multiview collaborative sparse unmixing for hyperspectral imagesIEEE Trans. Geosci. Remote Sens.5887668779
  18. K. Wang, J. Zhang, and D. Li2007Adaptive affinity propagation clusteringActa Autom. Sin.3312421246
  19. B. J. Frey and D. Dueck2007Clustering by passing messages between data pointsScience315972976
  20. Y. Liu, J. Li, A. Plaza, J. Bioucas-Dias, A. Cuartero, and P. G. RodriguezSpectral partitioning for hyperspectral remote sensing image classificationProc. IEEE Geoscience and Remote Sensing SymposiumJul. 2014QC, Canada34343437
  21. Y. Liu, J. Li, and A. Plaza2016Spectrometer-driven spectral partitioning for hyperspectral image classificationIEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.9668680
  22. S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein2010Distributed optimization and statistical learning via the alternating direction method of multipliersFound. Trends Mach. Learn.31122
  23. Z. Shi, W. Tang, Z. Duren, and Z. Jiang2014Subspace matching pursuit for sparse unmixing of hyperspectral dataIEEE Trans. Geosci. Remote Sens.5232563274
  24. S. Zhang, J. Li, Z. Wu, and A. Plaza2018Spatial discontinuity-weighted sparse unmixing of hyperspectral imagesIEEE Trans. Geosci. Remote Sens.5657675779
  25. R. A. Borsoi, T. Imbiriba, J. C. M. Bermudez, and C. Richard2019A fast multiscale spatial regularization for sparse hyperspectral unmixingIEEE Geosci. Remote Sens. Lett.16598602
  26. H. Li, R. Feng, L. Wang, Y. Zhong, and L. Zhang2021Superpixel-based reweighted low-rank and total variation sparse unmixing for hyperspectral remote sensing imageryIEEE Trans. Geosci. Remote Sens.59629647
  27. S. Zhang, J. Li, K. Liu, C. Deng, L. Liu, and A. Plaza2016Hyperspectral unmixing based on local collaborative sparse regressionIEEE Geosci. Remote Sens. Lett.13631635
  28. U.S. Geological Survey1995Spectroscopy LabU.S. Geological Surveyhttp://speclab.cr.usgs.gov/cuprite95.tgif.2.2um_map.gifAccessed date: 5 November 2020

Other (28)

N. Keshava and J. F. Mustard2002Spectral unmixingIEEE Signal Process. Mag.194457

J. M. Bioucas-Dias, A. Plaza, N. Dobigeon, M. Parente, Q. Du, P. Gader, and J. Chanussot2012Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approachesIEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.5354379

M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza2011Sparse unmixing of hyperspectral dataIEEE Trans. Geosci. Remote Sens.4920142039

M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza2014Collaborative sparse regression for hyperspectral unmixingIEEE Trans. Geosci. Remote Sens.52341354

C. Y. Zheng, H. Li, Q. Wang, and C. L. P. Chen2016Reweighted sparse regression for hyperspectral unmixingIEEE Trans. Geosci. Remote Sens.54479488

R. Wang, H.-C. Li, W. Liao, and A. Pi┼żuricaDouble reweighted sparse regression for hyperspectral unmixingProc. IEEE International Geoscience and Remote Sensing Symposium - IGARSSJul. 2016Beijing, China69866989

Z. Shi, T. Shi, M. Zhou, and X. Xu2018Collaborative sparse hyperspectral unmixing using l0 normIEEE Trans. Geosci. Remote Sens.5654955508

M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza2012Total variation spatial regularization for sparse hyperspectral unmixingIEEE Trans. Geosci. Remote Sens.5044844502

X. Li, J. Huang, L.-J. Deng, and T.-Z. Huang2019Bilateral filter based total variation regularization for sparse hyperspectral image unmixingInf. Sci.504334353

J. Huang, T.-Z. Huang, X.-L. Zhao, and L.-J. Deng2019Joint-sparse-blocks regression for total variation regularized hyperspectral unmixingIEEE Access7138779138791

S. Zhang, J. Li, H.-C. Li, C. Deng, and A. Plaza2018Spectral-spatial weighted sparse regression for hyperspectral image unmixingIEEE Trans. Geosci. Remote Sens.5632653276

P. V. Giampouras, K. E. Themelis, A. A. Rontogiannis, and K. D. Koutroumbas2016Simultaneously sparse and low-rank abundance matrix estimation for hyperspectral image unmixingIEEE Trans. Geosci. Remote Sens.5447754789

J. Huang, T. Z. Huang, L. J. Deng, and X. L. Zhao2019Joint-sparse-blocks and low-rank representation for hyperspectral unmixingIEEE Trans. Geosci. Remote Sens.5724192438

H. Han, G. Wang, M. Wang, J. Miao, S. Guo, L. Chen, M. Zhang, and K. Guo2020Hyperspectral unmixing via nonconvex sparse and low-rank constraintIEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.1357045718

R. Ammanouil, J. A. Melhem, J. Farah, and P. HoneineSpectral partitioning and fusion techniques for hyperspectral data classification and unmixingProc. 6th International Symposium on Communications, Control and Signal Processing - ISCCSPMay. 2014Athens, Greece550553

L. Qi, J. Li, Y. Wang, and X. Gao2019Region-based multiview sparse hyperspectral unmixing incorporating spectral libraryIEEE Geosci. Remote Sens. Lett.1611401144

L. Qi, J. Li, Y. Wang, Y. Huang, and X. Gao2020Spectral-spatial-weighted multiview collaborative sparse unmixing for hyperspectral imagesIEEE Trans. Geosci. Remote Sens.5887668779

K. Wang, J. Zhang, and D. Li2007Adaptive affinity propagation clusteringActa Autom. Sin.3312421246

B. J. Frey and D. Dueck2007Clustering by passing messages between data pointsScience315972976

Y. Liu, J. Li, A. Plaza, J. Bioucas-Dias, A. Cuartero, and P. G. RodriguezSpectral partitioning for hyperspectral remote sensing image classificationProc. IEEE Geoscience and Remote Sensing SymposiumJul. 2014QC, Canada34343437

Y. Liu, J. Li, and A. Plaza2016Spectrometer-driven spectral partitioning for hyperspectral image classificationIEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.9668680

S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein2010Distributed optimization and statistical learning via the alternating direction method of multipliersFound. Trends Mach. Learn.31122

Z. Shi, W. Tang, Z. Duren, and Z. Jiang2014Subspace matching pursuit for sparse unmixing of hyperspectral dataIEEE Trans. Geosci. Remote Sens.5232563274

S. Zhang, J. Li, Z. Wu, and A. Plaza2018Spatial discontinuity-weighted sparse unmixing of hyperspectral imagesIEEE Trans. Geosci. Remote Sens.5657675779

R. A. Borsoi, T. Imbiriba, J. C. M. Bermudez, and C. Richard2019A fast multiscale spatial regularization for sparse hyperspectral unmixingIEEE Geosci. Remote Sens. Lett.16598602

H. Li, R. Feng, L. Wang, Y. Zhong, and L. Zhang2021Superpixel-based reweighted low-rank and total variation sparse unmixing for hyperspectral remote sensing imageryIEEE Trans. Geosci. Remote Sens.59629647

S. Zhang, J. Li, K. Liu, C. Deng, L. Liu, and A. Plaza2016Hyperspectral unmixing based on local collaborative sparse regressionIEEE Geosci. Remote Sens. Lett.13631635

U.S. Geological Survey1995Spectroscopy LabU.S. Geological Surveyhttp://speclab.cr.usgs.gov/cuprite95.tgif.2.2um_map.gifAccessed date: 5 November 2020

Cited By

Optica participates in Crossref's Cited-By Linking service. Citing articles from Optica Publishing Group journals and other participating publishers are listed here.