the image. (3)
K-SVD
is used to reduce the error between the
estimated endmember and the initial endmember in the itera-
tive calculation process, and the final optimized endmember
matrix is obtained. The experimental results confirm that the
proposed method has good algorithm adaptability and excel-
lent optimization results, which can improve the endmember
accuracy by 15.1%–55.7%.
Acknowledgments
This work was supported by the National Key R & D plan on
strategic international scientific, technological innovation co-
operation special project (2016YFE0202300) and the National
Natural Science Foundation of China (61671332, 41771452,
and 41771454). The authors would like to thank the anony-
mous reviewers for their hard work.
References
Addink, E. A., S. M. De Jong and E. J. Pebesma. 2007. The importance
of scale in object-based mapping of vegetation parameters
with hyperspectral imagery.
Photogrammetric Engineering and
Remote Sensing
73 (8):905–912.
Aharon, M., M. Elad and A. Bruckstein. 2006.
K-SVD
: An
algorithm for designing overcomplete dictionaries for sparse
representation.
IEEE Transactions on Signal Processing
54
(11):4311–4322. doi: 10.1109/TSP.2006.881199.
Donoho, D. L. 2006. For most large underdetermined systems of
linear equations the minimal
l
1-norm solution is also the
sparsest solution.
Communications on Pure and Applied
Mathematics: A Journal Issued by the Courant Institute of
Mathematical Sciences
59 (6):797–829. Wiley Online Library.
Hong, D., N. Yokoya, J. Chanussot and X. X. Zhu 2017. Learning a
low-coherence dictionary to address spectral variability for
hyperspectral unmixing. In
2017 IEEE International Conference
on Image Processing (ICIP)
, held in Beijing, China.
Keshava, N. and J. F. Mustard. 2002. Spectral unmixing.
IEEE Signal
Processing Magazine
19 (1):44–57. doi: 10.1109/79.974727.
Li, H., J. Ma, J. Liu, M. Gong and M. Zhang
.
2017. Multi-objective
endmember extraction for hyperspectral images. Pages 458–465
in
2017 IEEE Congress on Evolutionary Computation (CEC)
, held
in San Sebastian, Spain. doi: 10.1109/CEC.2017.7969347.
Li, J. and Jun Li ; J.ose M. Bioucas-Dias. 2008.
simplex analysis : A fast algorithm to un
data. Pages 250–253 In IGARSS 2008 -
2
Geoscience and Remote Sensing Sympos
MAass. doi: 10.1109/IGARSS.2008.4779
Liu, X., W. Xia, B. Wang and L. Zhang. 2011. An approach based
on constrained nonnegative matrix factorization to unmix
hyperspectral data.
IEEE Transactions on Geoscience and
Remote Sensing
49 (2): 757–772.
Liu, Y., Y. Guo, F. Li, L. Xin and P. Huang. 2018. Sparse dictionary
learning for blind hyperspectral unmixing.
IEEE Geoscience and
Remote Sensing Letters
1–5. doi: 10.1109/LGRS.2018.2878036.
Lu, X., H. Wu and Y. Yuan. 2014 Double constrained NMF for
hyperspectral unmixing.
IEEE Transactions on Geoscience
and Remote Sensing
52 (5): 2746–2758. doi: 10.1109/
TGRS.2013.2265322.
Miao, L. and H. Qi. 2007. Endmember extraction from highly mixed
data using minimum volume constrained nonnegative matrix
factorization.
IEEE Transactions on Geoscience and Remote
Sensing
45 (3): 765–777. doi: 10.1109/TGRS.2006.888466.
Nascimento, J. M. P. and J. M. B. Dias. 2005. Vertex component
analysis: A fast algorithm to unmix hyperspectral data.
IEEE
Transactions on Geoscience and Remote Sensing
43 (4):898–910.
Ramirez, I. and G. Sapiro. 2012. Universal regularizers for robust
sparse coding and modeling.
IEEE Transactions on Image
Processing
21 (9):3850–3864.
Romberg, J. 2008 Imaging via compressive sampling (introduction to
compressive sampling and recovery via convex programming).
IEEE Signal Processing Magazine
25 (2):14–20.
Shao, Z. and L. Zhang. 2014. Sparse dimensionality reduction of
hyperspectral image based on semi-supervised local Fisher
discriminant analysis.
International Journal of Applied Earth
Observation and Geoinformation
31:122–129.
Sun, W., J. Ma, G. Yang, B. Du and L. Zhang. 2017. A Poisson
nonnegative matrix factorization method with parameter
subspace clustering constraint for endmember extraction in
hyperspectral imagery.
ISPRS Journal of Photogrammetry and
Remote Sensing
128:27–39.
Sun, W., D. Zhang, Y. Xu, L. Tian, G. Yang and W. Li. 2017. A
probabilistic weighted archetypal analysis method with Earth
mover’s distance for endmember extraction from hyperspectral
imagery.
Remote Sensing
9 (8):841.
Sun, W., Y. Gang, K. Wu, W. Li and D. Zhang. 2017. Pure endmember
extraction using robust kernel archetypoid analysis for
hyperspectral imagery.
ISPRS Journal of Photogrammetry and
Remote Sensing
131:147–159.
Wang, X., Y. Zhong, L. Zhang and Y. Xu. 2017. Spatial group sparsity
regularized nonnegative matrix factorization for hyperspectral
unmixing.
IEEE Transactions on Geoscience and Remote Sensing
55 (11): 6287–6304.
Winter, M. E. 1999. N-FINDR: An algorithm for fast autonomous
spectral end-member determination in hyperspectral data.
Proceedings of SPIE—The International Society for Optical
Engineering
3753:266–275.
Xu, B. and P. Gong. 2007. Land-use/land-cover classification with
multispectral and hyperspectral EO-1 data.
Photogrammetric
Engineering and Remote Sensing
73 (8):955–965.
Xu, M., B. Du and Y. Fan. 2019. Using linear mixture model
constrained particle swarm optimization. 57 (8):5502–5511. doi:
.2899826.
, S. Ding, J.-M. Yang and J. Zhang. 2011.
ixing based on sparse nonnegative matrix
Transactions on Image Processing
20
(4):1112–1125.
Zhang, C. and F. Qiu. 2012. Mapping individual tree species in an
urban forest using airborne lidar data and hyperspectral imagery.
Photogrammetric Engineering and Remote Sensing
78 (10):1079–
1087.
Zhong, Y., X. Wang, L. Zhao, R. Feng, L. Zhang and Y. Xu. 2016.
Blind spectral unmixing based on sparse component analysis
for hyperspectral remote sensing imagery.
ISPRS Journal of
Photogrammetry and Remote Sensing
119:49–63. doi: 10.1016/j.
isprsjprs.2016.04.008.
PHOTOGRAMMETRIC ENGINEERING & REMOTE SENSING
December 2019
887
