Hyperspectral Image Unmixing Based on Constrained Nonnegative Matrix Factorization

Shuai Fang; Jinming Wang; Fengyun Cao

doi:10.3788/LOP56.161001

Laser & Optoelectronics Progress, Volume. 56, Issue 16, 161001(2019)

Hyperspectral Image Unmixing Based on Constrained Nonnegative Matrix Factorization

Shuai Fang^1、**, Jinming Wang^1、*, and Fengyun Cao^2,3

¹ Department of Artificial Intelligence and Data Mining, School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui 230601, China

² Anhui Provincial Key Laboratory of Industry Safety and Emergency Technology, Hefei University of Technology, Hefei, Anhui 230601, China

³ School of Computer Science and Technology, Hefei Normal University, Hefei, Anhui 230601, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(14)

Fig. 1. Procedure of SSPP-CNMF algorithm

Download full size

Fig. 2. Hyperspectral images. (a) Fractal1; (b) Jasper; (c) Cuprite

Download full size

Fig. 3. Jasper ground truths (GT) and endmember results obtained by proposed algorithm. (a) Tree; (b) soil; (c) water; (d) road

Download full size

Fig. 4. Ground truths of Jasper abundance. (a) Water; (b) soil; (c) road; (d) tree

Download full size

Fig. 5. Jasper abundances estimated by VCA algorithm. (a) Water; (b) soil; (c) road; (d) tree

Download full size

Fig. 6. Jasper abundances estimated by CoNMF algorithm. (a) Water; (b) soil; (c) road; (d) tree

Download full size

Fig. 7. Jasper abundances estimated by MVC-NMF algorithm. (a) Water; (b) soil; (c) road; (d) tree

Download full size

Fig. 8. Jasper abundances estimated by SSPP-VCA algorithm. (a) Water; (b) soil; (c) road; (d) tree

Download full size

Fig. 9. Jasper abundances estimated by SSPP-CNMF algorithm. (a) Water; (b) soil; (c) road; (d) tree

Download full size

Fig. 10. Fractal1 abundances estimated by SSPP-CNMF algorithm. (a) Halloysite; (b) Nontronite; (c) Kaolinite CM9; (d) Sphene; (e) Muscovite; (f) Kaolinite KGa1; (g) Dumortierite; (h) Pyrophyllite; (i) Alunite

Download full size

Fig. 11. Fractal1 ground truth and endmember spectra estimated by SSPP-CNMF algorithm. (a) Dumortierite; (b) Halloysite; (c) Kaolinite CM9; (d) Kaolinite KGa1; (e) Muscovite; (f) Nontronite; (g) Pyrophyllite; (h) Sphene

Download full size

Fig. 12. Cuprite abundances estimated by SSPP-CNMF algorithm. (a) Endmember 1;(b) Endmember 2; (c) Endmember 3; (d) Endmember 4; (e) Endmember 5; (f) Endmember 6; (g) Endmember 7; (h) Endmember 8; (i) Endmember 9; (j) Endmember 10; (k) Endmember 11; (l) Endmember 12

Download full size

Table 1. Comparison of SAD of different hyperspectral unmixing algorithms
View table
Table 1. Comparison of SAD of different hyperspectral unmixing algorithms
Hyperspectral datasets SNR /dB SAD /10^-2
VCA MVSA MVC-NMF CoNMF SSPP-VCA Ours
Fractal1 30 20.32 22.46 17.51 9.68 11.37 9.31
Jasper 41.63 28.42 24.42 29.43 12.82 12.71
Cuprite 25.08 12.42 20.22 19.71 13.32 13.22

Table 2. Comparison of RMSE of different hyperspectral unmixing algorithms
View table
Table 2. Comparison of RMSE of different hyperspectral unmixing algorithms
Hyperspectral datasets SNR /dB RMSE /10^-2
VCA MVSA MVC-NMF CoNMF SSPP-VCA Ours
Fractal1 30 24.19 22.71 15.37 10.68 13.44 10.52
Jasper 36.61 38.81 19.75 26.72 19.39 18.78
Cuprite — — — — — —

Tools

Get Citation

Copy Citation Text

Shuai Fang, Jinming Wang, Fengyun Cao. Hyperspectral Image Unmixing Based on Constrained Nonnegative Matrix Factorization[J]. Laser & Optoelectronics Progress, 2019, 56(16): 161001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites