Hierarchical Sparse Learning with Spectral-Spatial Information for Hyperspectral Imagery Denoising

Abstract

During the acquisition process hyperspectral images (HSI) are inevitably corrupted by various noises, which greatly influence their visual impression and subsequent applications. In this paper, a novel Bayesian approach integrating hierarchical sparse learning and spectral-spatial information is proposed for HSI denoising. Based on the structure correlations, spectral bands with similar and continuous features are segmented into the same band-subset. To exploit local similarity, each subset is then divided into overlapping cubic patches. All patches can be regarded as consisting of clean image component, Gaussian noise component and sparse noise component. The first term is depicted by a linear combination of dictionary elements, where Gaussian process with Gamma distribution is applied to impose spatial consistency on dictionary. The last two terms are utilized to fully depict the noise characteristics. Furthermore, the sparseness of the model is adaptively manifested through Beta-Bernoulli process. Calculated by Gibbs sampler, the proposed model can directly predict the noise and dictionary without priori information of the degraded HSI. The experimental results on both synthetic and real HSI demonstrate that the proposed approach can better suppress the existing various noises and preserve the structure/spectral-spatial information than the compared state-of-art approaches.

Hyperspectral Images Reconstruction based on the 3D Fast Super-Resolution Convolutional Neural Networks

“…In 2017, Galliani and others to try in the spectral dimension of hyperspectral image super-resolution, prove the feasibility and advantage of the convolution spectrum dimension of [1], to solve the problems of the spectral distortion also provides a new way of thinking. In the application of hyperspectral based on CNN, Makantasis et al used random principal component analysis (RPCA) [2] to integrate spatial-spectral information into CNN, but the information would be lost, so the spatial-spectral characteristics provided to CNN by RPCA could not be directly extended to the super-resolution. To explore the hyperspectral image super-resolution spatial context and space spectrum identification, Mei et al, this paper proposes a threedimensional full convolution neural network (3D -FCNN) framework [3], using three-dimensional convolution operation to study between the adjacent pixels of space environment and the spectral correlation of adjacent band image, thus reduce the spectral distortion, but this method is still lacking in computational efficiency.…”

An Effective Classification Scheme for Hyperspectral Image Based on Superpixel and Discontinuity Preserving Relaxation

“…Among of the spectral-spatial based approaches, some spatial filtering techniques are developed [23][24][25][26][27][28]. The purpose of applying these techniques to HSI classification is to denoise HSI in the pre-processing task or improve the classification accuracy in post-processing.…”

A Denoising Scheme for Randomly Clustered Noise Removal in ICCD Sensing Image

“…The general idea of this method is to learn a large group of patches from an image dataset to form a redundancy dictionary, such that each patch in the reconstructed image can be expressed as a linear combination of a few patches in the dictionary. There have been plenty of dictionary learning based denoising methods, such as K-clustering with singular value decomposition (K-SVD) [ 40 ], learned simultaneous sparse coding (LSSC) [ 41 ], clustering-based sparse representation (CSR) [ 42 ], hierarchical sparse learning with spectral-spatial information [ 43 ], and vector-valued sparse representation model using reduced quaternion matrix [ 44 ].…”