Local spectral similarity preserving regularized robust sparse hyperspectral unmixing

Jiaojiao Li, Yunsong Li, Rui Song, Shaohui Mei, Qian Du

科研成果: 期刊稿件文章同行评审

41 引用 (Scopus)

摘要

Spatial context has been demonstrated to be effective to constrain sparse unmixing (SU) of hyperspectral images. However, the existing algorithms employed simple spatial information without keeping spectral fidelity. By considering the fact that adjacent pixels own not only the endmembers with same variations but also approximated fractional abundances, in this paper, local spectral similarity preserving (LSSP) constraint is proposed to preserve spectral similarity in a local area during robust sparse unmixing (RSU). Specially, four LSSP constraints are constructed using different-norm-constrained pixel-level difference over abundance-level difference in a local area. Moreover, a convex optimization algorithm is proposed to solve the proposed LSSP-constrained RSU (LSSP-RSU). Experimental results on both synthetic and real hyperspectral data demonstrate that the developed algorithms yield better values of the signal-to-reconstruction error (SRE). Especially, when using l2 norm of pixel-level difference to weight the l1 norm of abundance-level difference, the proposed LSSP-RSU algorithm can achieve superior unmixing performance.

源语言英语
文章编号8732595
页(从-至)7756-7769
页数14
期刊IEEE Transactions on Geoscience and Remote Sensing
57
10
DOI
出版状态已出版 - 10月 2019

指纹

探究 'Local spectral similarity preserving regularized robust sparse hyperspectral unmixing' 的科研主题。它们共同构成独一无二的指纹。

引用此