Efficient Two-Phase Multiobjective Sparse Unmixing Approach for Hyperspectral Data

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Mingliang Xu¹  Xiangming Jiang²  Tao Zhan²  Maoguo Gong³  Kai Sheng³ 

[1] School of Computer Science and Technology, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi&x2019;School of Electronic Engineering, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi&x2019;an, China;

关键词: Composite spectral similarity measure;    highly noisy data;    $ {L_{2,\infty }}$ norm;    multiobjective sparse unmixing;    spatial-contextual information;    time efficiency;   

DOI  :  10.1109/JSTARS.2021.3054926

来源: DOAJ

【 摘 要 】

In our previous work, a two-phase multiobjective sparse unmixing (Tp-MoSU) approach has been proposed, which settled the regularization parameter issues of the regularization unmixing methods. However, Tp-MoSU has limited performance in identifying the real end-members from the highly noisy data in the first phase and cannot effectively exploit the spatial-contextual information in the second phase because of the similarity measure it used. To settle these two problems, a composite spectral similarity measure is first constructed by fusing the spectral correlation angle and the Euclidean distance. It is used instead of the Frobenius norm to measure the unmixing residuals in the first phase because it considers both the shape and amplitude discrepancy between two spectra simultaneously. Then, the L_2,∞ norm is used instead of the l₂ norm to measure the unmixing residuals in the second phase, and the initialization, recombination, mutation, and local search strategies are also elaborately redesigned to help reduce this new objective, based on which the unmixing tasks of all pixels in a hyperspectral image can be completed at once. Therefore, this new measure facilitates the estimation of the abundances as a whole, and thus, the spatial-contextual information can be better exploited to improve the estimated abundances. Besides, the time efficiency for abundance estimation is also greatly improved. Experimental results demonstrate that the proposed method (termed as TpMoSU+) outperforms Tp-MoSU in both of the two phases under heavy noise and outperforms the tested regularization algorithms in estimating the abundances.

【 授权许可】

Unknown