Abstract
The majority of existing hyperspectral (HS) image denoising methods exploit local similarity in HS images by rearranging them into the matrix or vector forms. As the typical 3-D data, the inherent spatial and spectral properties in HS images should be simultaneously explored for denoising. Therefore, a 3-D geometrical kernel (3DGK) is developed in this article to describe the local structure. The proposed method assumes that the pixel can be represented by other pixels within a 3-D block efficiently owing to the local similarity with adjacent positions. Then, the HS image is modeled by the 3-D kernel regression with L 1-norm constraint, in which the local similarity is captured by the proposed 3DGK. To efficiently compute the parameters in 3DGK, geometrical structures, such as scale, shape, and orientation in the 3-D block, are estimated from the gradient information approximately. Finally, the noises are effectively removed while preserving the structures in HS images. Moreover, experimental results on simulated and real datasets demonstrate that the performance of 3DGK is better than those of the methods based on local similarity prior.
Highlights
W ITH the rapid development of imaging sensors, hyperspectral (HS) remote sensing technology has been attracting much attention and HS images have been applied in many scene interpretation tasks, such as land-use classification [1], target detection [2], and unmixing [3]–[6], due to containing abundant spectral information
1) We present a novel 3-D geometrical kernel (3DGK) regression model for HS images denoising, which adopts the geometrical structures in 3-D blocks to capture the local similarity (LS) in spatial and spectral domains
An HS image denoising method is developed by extending the kernel regression model to the 3-D formulation, which makes effective use of the spatial and spectral geometrical structures in HS images
Summary
W ITH the rapid development of imaging sensors, hyperspectral (HS) remote sensing technology has been attracting much attention and HS images have been applied in many scene interpretation tasks, such as land-use classification [1], target detection [2], and unmixing [3]–[6], due to containing abundant spectral information. Zhao and Yang [28] utilized sparse and low-rank constraints to capture the local redundancy and correlation in HS images, which can well preserve the spatial and spectral details in the denoised HS images. The spectral information is represented by a fixed vector in [40], which cannot adaptively estimate the features in the spectral direction These methods obtain better denoised HS images, the inner structures in 3-D blocks of HS images are not analyzed carefully and deeply. 1) We present a novel 3DGK regression model for HS images denoising, which adopts the geometrical structures in 3-D blocks to capture the LS in spatial and spectral domains. ZHANG et al.: HYPERSPECTRAL IMAGE DENOISING USING 3-D GEOMETRICAL KERNEL WITH LOCAL SIMILARITY PRIOR
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: 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.
