Piecewise Weighted Smoothing Regularization in Tight Framelet Domain for Hyperspectral Image Restoration

Abstract

Hyperspectral images captured by remote-sensing satellites are easily corrupted by various types of noise. Generally, hyperspectral signatures appear to be scattered in spatial-spectral domain, as well as noise. In transform domain, however, the principal components of a image are often centralized in the low-frequency band, while noise and some details are mainly contained in high-frequency components. The traditional transformation domain based smoothing methods take no account of the respective information distribution carried by different frequency bands. Hyperspectral image restoration aims to remove mixed noise for clean data, which usually amounts to an ill-posed inverse problem. Moreover, the matrixdecomposition-based model needs to reshape hyperspectral datacube into matrix form, which will lead to certain loss of spatial structure information. In order to address these issues, this paper incorporates piecewise weighted smoothing regularization in tight framelet domain to reformulate a novel convex model for hyperspectal image restoration, which maintains image signature to a great extent. Based on the noise-perturbed degradation model, the smoothing regularizer in tight framelet domain is imposed on abundance signature, in which the transformation matrix, as well as the weighted coefficient, is well designed for different frequency bands. As a surrogate of sparsity, the l q -norm is employed to denoise for the enhancement of hyperspectral signatures. To the end, an efficient solver is carefully designed to derive the closed-form solutions by proximal alternating optimization. The experimental results on several synthetic and real datasets, not only demonstrate that the performance of proposed method is better than that of the current state-of-the-art approaches, but also verify the validation of regularization terms for hyperspectral image restoration.INDEX TERMS Hyperspectral image restoration, tight framelet domain, piecewise weighted smoothing;degradation model, mixed noise

A Noise Estimation Method for Hyperspectral Image Based on Stacked Autoencoder

“…In this section, we describe how to achieve hyperspectral noise estimation using autoencoders. The method in this paper is mainly composed of the following parts: (1) K-means algorithm for classification; (2) The autoencoder is used to reconstruct the image in each homogeneous region; (3) The reconstructed image is different from the original image to achieve signal-to-noise separation; (4) Divides the original image into a large number of subblocks, detects the edges of the original image and removes the subblocks that contain the edges; (5) the standard deviation of the remaining subblocks is calculated and the noise value is estimated. Fig.…”

“…Hyperspectral images are data cubes with high spectral resolution obtained by imaging spectrometers, which can record the two-dimensional geometric distribution of objects in the field of view and the continuous spectral curve of each pixel position [1], [2]. The detector needs to respond to hundreds of narrowband channel image signals in a short time, and the received signal energy is limited, resulting in a low signal-noise ratio of the acquired hyperspectral images.…”