Abstract
Recently, sparse unmixing has received particular attention in the analysis of hyperspectral images (HSIs). However, traditional sparse unmixing ignores the different noise levels in different bands of HSIs, making such methods sensitive to different noise levels. To overcome this problem, the noise levels at different bands are assumed to be different in this paper, and a general sparse unmixing method based on noise level estimation (SU-NLE) under the sparse regression framework is proposed. First, the noise in each band is estimated on the basis of the multiple regression theory in hyperspectral applications, given that neighboring spectral bands are usually highly correlated. Second, the noise weighting matrix can be obtained from the estimated noise. Third, the noise weighting matrix is integrated into the sparse regression unmixing framework, which can alleviate the impact of different noise levels at different bands. Finally, the proposed SU-NLE is solved by the alternative direction method of multipliers. Experiments on synthetic datasets show that the signal-to-reconstruction error of the proposed SU-NLE is considerably higher than those of the corresponding traditional sparse regression unmixing methods without noise level estimation, which demonstrates the efficiency of integrating noise level estimation into the sparse regression unmixing framework. The proposed SU-NLE also shows promising results in real HSIs.
Highlights
Hyperspectral imaging has been a widely used commodity, and hyperspectral image (HSI) is intrinsically a data cube which has two spatial dimensions and a spectral dimension
The signal-to-reconstruction error (SRE) of SU-NLE (d = 1) and SU-NLE (d = 2) are higher than those of SUnSAL and CLSUnSAL when λ < 102, respectively, because SU-NLE (d = 1) and SU-NLE (d = 2) adopt the weighting strategy that considers the different noise levels of different bands, which demonstrates the efficiency of integrating noise level estimation into the sparse regression unmixing framework
We propose a general sparse unmixing method based on noise level estimation
Summary
Hyperspectral imaging has been a widely used commodity, and hyperspectral image (HSI) is intrinsically a data cube which has two spatial dimensions (width and height) and a spectral dimension. Spectral unmixing is essential as it aims at decomposing mixed pixels into a collection of pure spectral signatures, called endmembers, and their corresponding proportions in each pixel, called abundances [16,17]. To address this problem, linear mixing model (LMM) has been extensively applied in the fields of geoscience and remote sensing processing due to its relative simplicity and straightforward interpretation [15]. A semi-supervised unmixing method assumes that a mixed pixel can be formulated in the form of linear combinations of numerous pure spectral signatures (library) known in advance and finds the optimal subset of signatures to optimally model the mixed pixel in the scene, which leads to a sparse solution [27]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
