TY - GEN
T1 - Hyperspectral image fusion based on non-factorization sparse representation and error matrix estimation
AU - Han, Xiaolin
AU - Luo, Jiqiang
AU - Yu, Jing
AU - Sun, Weidong
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - Matrix factorization with non-negative constrains is widely used in hyperspectral image fusion. Nevertheless, the non-negative restriction on the sparse coefficients limits the efficiency of dictionary representation. To solve this problem, a new hyperspectral image fusion method based on non-factorization sparse representation and error matrix estimation is proposed in this paper, for the fusion of remotely sensed high-spatial multi-bands image with low-spatial hyperspectral image in the same scene. Firstly, an efficient spectral dictionary learning method is specifically adopted for the construction of the spectral dictionary, which avoids the procedure of matrix factorization. Then, the sparse codes of the high-spatial multi-bands image with respect to the learned spectral dictionary are estimated using the alternating direction method of multipliers (ADMM) without non-negative constrains. For improving the quality of final fusion result, an error matrix estimation method is also proposed, exploiting the spatial structure information after non-factorization sparse representation. Experimental results both on simulated and real datasets demonstrate that, compared with the related state-of-the-art methods, our proposed method achieves the highest quality of hyperspectral image fusion, which can improve PSNR over 2.5844 and SAM over 0.3758.
AB - Matrix factorization with non-negative constrains is widely used in hyperspectral image fusion. Nevertheless, the non-negative restriction on the sparse coefficients limits the efficiency of dictionary representation. To solve this problem, a new hyperspectral image fusion method based on non-factorization sparse representation and error matrix estimation is proposed in this paper, for the fusion of remotely sensed high-spatial multi-bands image with low-spatial hyperspectral image in the same scene. Firstly, an efficient spectral dictionary learning method is specifically adopted for the construction of the spectral dictionary, which avoids the procedure of matrix factorization. Then, the sparse codes of the high-spatial multi-bands image with respect to the learned spectral dictionary are estimated using the alternating direction method of multipliers (ADMM) without non-negative constrains. For improving the quality of final fusion result, an error matrix estimation method is also proposed, exploiting the spatial structure information after non-factorization sparse representation. Experimental results both on simulated and real datasets demonstrate that, compared with the related state-of-the-art methods, our proposed method achieves the highest quality of hyperspectral image fusion, which can improve PSNR over 2.5844 and SAM over 0.3758.
KW - dictionary learning
KW - error matrix estimation
KW - hyperspectral image fusion
KW - non-factorization sparse representation
UR - https://www.scopus.com/pages/publications/85048066301
U2 - 10.1109/GlobalSIP.2017.8309142
DO - 10.1109/GlobalSIP.2017.8309142
M3 - Conference contribution
AN - SCOPUS:85048066301
T3 - 2017 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2017 - Proceedings
SP - 1155
EP - 1159
BT - 2017 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE Global Conference on Signal and Information Processing, GlobalSIP 2017
Y2 - 14 November 2017 through 16 November 2017
ER -