Current Optics and Photonics

Optical Society of Korea (한국광학회)
권호 표지
DOI QR코드

DOI QR Code

Multiview-based Spectral Weighted and Low-Rank for Row-sparsity Hyperspectral Unmixing

  • Zhang, Shuaiyang (Department of Electronic and Optical Engineering, Army Engineering University of PLA) ;
  • Hua, Wenshen (Department of Electronic and Optical Engineering, Army Engineering University of PLA) ;
  • Liu, Jie (Department of Electronic and Optical Engineering, Army Engineering University of PLA) ;
  • Li, Gang (Department of Electronic and Optical Engineering, Army Engineering University of PLA) ;
  • Wang, Qianghui (Department of Electronic and Optical Engineering, Army Engineering University of PLA)
  • Received : 2021.02.23
  • Accepted : 2021.05.24
  • Published : 2021.08.25
Download PDF
⟨ Previous Next ⟩

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.

Keywords

References

  1. N. Keshava and J. F. Mustard, "Spectral unmixing," IEEE Signal Process. Mag. 19, 44-57 (2002). https://doi.org/10.1109/79.974727
  2. J. M. Bioucas-Dias, A. Plaza, N. Dobigeon, M. Parente, Q. Du, P. Gader, and J. Chanussot, "Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches," IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 5, 354-379 (2012). https://doi.org/10.1109/JSTARS.2012.2194696
  3. M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza, "Sparse unmixing of hyperspectral data," IEEE Trans. Geosci. Remote Sens. 49, 2014-2039 (2011). https://doi.org/10.1109/TGRS.2010.2098413
  4. M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza, "Collaborative sparse regression for hyperspectral unmixing," IEEE Trans. Geosci. Remote Sens. 52, 341-354 (2014). https://doi.org/10.1109/TGRS.2013.2240001
  5. C. Y. Zheng, H. Li, Q. Wang, and C. L. P. Chen, "Reweighted sparse regression for hyperspectral unmixing," IEEE Trans. Geosci. Remote Sens. 54, 479-488 (2016). https://doi.org/10.1109/TGRS.2015.2459763
  6. R. Wang, H.-C. Li, W. Liao, and A. Pizurica, "Double reweighted sparse regression for hyperspectral unmixing," in Proc. IEEE International Geoscience and Remote Sensing Symposium - IGARSS (Beijing, China, Jul. 2016), pp. 6986-6989.
  7. Z. Shi, T. Shi, M. Zhou, and X. Xu, "Collaborative sparse hyperspectral unmixing using l0 norm," IEEE Trans. Geosci. Remote Sens. 56, 5495-5508 (2018). https://doi.org/10.1109/TGRS.2018.2818703
  8. M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza, "Total variation spatial regularization for sparse hyperspectral unmixing," IEEE Trans. Geosci. Remote Sens. 50, 4484-4502 (2012). https://doi.org/10.1109/TGRS.2012.2191590
  9. X. Li, J. Huang, L.-J. Deng, and T.-Z. Huang, "Bilateral filter based total variation regularization for sparse hyperspectral image unmixing," Inf. Sci. 504, 334-353 (2019). https://doi.org/10.1016/j.ins.2019.07.063
  10. J. Huang, T.-Z. Huang, X.-L. Zhao, and L.-J. Deng, "Joint-sparse-blocks regression for total variation regularized hyperspectral unmixing," IEEE Access 7, 138779-138791 (2019). https://doi.org/10.1109/ACCESS.2019.2943110
  11. S. Zhang, J. Li, H.-C. Li, C. Deng, and A. Plaza, "Spectral-spatial weighted sparse regression for hyperspectral image unmixing," IEEE Trans. Geosci. Remote Sens. 56, 3265-3276 (2018). https://doi.org/10.1109/TGRS.2018.2797200
  12. P. V. Giampouras, K. E. Themelis, A. A. Rontogiannis, and K. D. Koutroumbas, "Simultaneously sparse and low-rank abundance matrix estimation for hyperspectral image unmixing," IEEE Trans. Geosci. Remote Sens. 54, 4775-4789 (2016). https://doi.org/10.1109/TGRS.2016.2551327
  13. J. Huang, T. Z. Huang, L. J. Deng, and X. L. Zhao, "Joint-sparse-blocks and low-rank representation for hyperspectral unmixing," IEEE Trans. Geosci. Remote Sens. 57, 2419-2438 (2019). https://doi.org/10.1109/TGRS.2018.2873326
  14. H. Han, G. Wang, M. Wang, J. Miao, S. Guo, L. Chen, M. Zhang, and K. Guo, "Hyperspectral unmixing via nonconvex sparse and low-rank constraint," IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 13, 5704-5718 (2020). https://doi.org/10.1109/JSTARS.2020.3021520
  15. R. Ammanouil, J. A. Melhem, J. Farah, and P. Honeine, "Spectral partitioning and fusion techniques for hyperspectral data classification and unmixing," in Proc. 6th International Symposium on Communications, Control and Signal Processing - ISCCSP (Athens, Greece, May. 2014), pp. 550-553.
  16. L. Qi, J. Li, Y. Wang, and X. Gao, "Region-based multiview sparse hyperspectral unmixing incorporating spectral library," IEEE Geosci. Remote Sens. Lett. 16, 1140-1144 (2019). https://doi.org/10.1109/LGRS.2019.2891559
  17. L. Qi, J. Li, Y. Wang, Y. Huang, and X. Gao, "Spectral-spatial-weighted multiview collaborative sparse unmixing for hyperspectral images," IEEE Trans. Geosci. Remote Sens. 58, 8766-8779 (2020). https://doi.org/10.1109/TGRS.2020.2990476
  18. K. Wang, J. Zhang, and D. Li, "Adaptive affinity propagation clustering," Acta Autom. Sin. 33, 1242-1246 (2007).
  19. B. J. Frey and D. Dueck, "Clustering by passing messages between data points," Science 315, 972-976 (2007). https://doi.org/10.1126/science.1136800
  20. Y. Liu, J. Li, A. Plaza, J. Bioucas-Dias, A. Cuartero, and P. G. Rodriguez, "Spectral partitioning for hyperspectral remote sensing image classification," in Proc. IEEE Geoscience and Remote Sensing Symposium (QC, Canada, Jul. 2014), pp. 3434-3437.
  21. Y. Liu, J. Li, and A. Plaza, "Spectrometer-driven spectral partitioning for hyperspectral image classification," IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 9, 668-680 (2016). https://doi.org/10.1109/JSTARS.2015.2437614
  22. S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein, "Distributed optimization and statistical learning via the alternating direction method of multipliers," Found. Trends Mach. Learn. 3, 1-122 (2010). https://doi.org/10.1561/2200000016
  23. Z. Shi, W. Tang, Z. Duren, and Z. Jiang, "Subspace matching pursuit for sparse unmixing of hyperspectral data," IEEE Trans. Geosci. Remote Sens. 52, 3256-3274 (2014). https://doi.org/10.1109/TGRS.2013.2272076
  24. S. Zhang, J. Li, Z. Wu, and A. Plaza, "Spatial discontinuityweighted sparse unmixing of hyperspectral images," IEEE Trans. Geosci. Remote Sens. 56, 5767-5779 (2018). https://doi.org/10.1109/TGRS.2018.2825457
  25. R. A. Borsoi, T. Imbiriba, J. C. M. Bermudez, and C. Richard, "A fast multiscale spatial regularization for sparse hyperspectral unmixing," IEEE Geosci. Remote Sens. Lett. 16, 598-602 (2019). https://doi.org/10.1109/LGRS.2018.2878394
  26. H. Li, R. Feng, L. Wang, Y. Zhong, and L. Zhang, "Superpixel-based reweighted low-rank and total variation sparse unmixing for hyperspectral remote sensing imagery," IEEE Trans. Geosci. Remote Sens. 59, 629-647 (2021). https://doi.org/10.1109/TGRS.2020.2994260
  27. S. Zhang, J. Li, K. Liu, C. Deng, L. Liu, and A. Plaza, "Hyperspectral unmixing based on local collaborative sparse regression," IEEE Geosci. Remote Sens. Lett. 13, 631-635 (2016). https://doi.org/10.1109/LGRS.2016.2527782
  28. U.S. Geological Survey, "Spectroscopy Lab," (U.S. Geological Survey, Published date: 1995), http://speclab.cr.usgs.gov/cuprite95.tgif.2.2um_map.gif (Accessed date: 5 November 2020).